
# os to manipulate files
import os
# Importing pandas to work with DataFrames.
import pandas as pd
# Importing numpy to general methods.
import numpy as np
import time
import datetime
from datetime import datetime, date,timedelta
# Importing the matplotlib to create graphics
import matplotlib 
import matplotlib.pyplot as plt
%matplotlib inline
matplotlib.style.use('ggplot')

# Import seaborn to better the visualization
import seaborn as sns
import plotly.graph_objs as go
from plotly.offline import download_plotlyjs, init_notebook_mode, plot, iplot
import plotly.express as px


# Scipy for statistics
from scipy import stats
from sklearn.metrics import mean_absolute_error,r2_score
from sklearn.model_selection import train_test_split
from sklearn import linear_model
from sklearn.preprocessing import PolynomialFeatures
from sklearn.linear_model import LinearRegression
from scipy import integrate, optimize

# ML libraries
import lightgbm as lgb
import xgboost as xgb
from xgboost import plot_importance, plot_tree
from sklearn.model_selection import RandomizedSearchCV, GridSearchCV
from sklearn import preprocessing, svm
from sklearn import linear_model
from sklearn.metrics import mean_squared_error,explained_variance_score
import sklearn
import matplotlib.dates as dates
import seaborn as seabornInstance 
from sklearn.linear_model import LinearRegression
from sklearn import metrics
from scipy.stats import zscore
from sklearn.preprocessing import StandardScaler
from sklearn.neighbors import KNeighborsClassifier
from sklearn.model_selection import cross_val_score
from matplotlib import rcParams
#sns.set()
#sns.set_context('talk')
import warnings
warnings.filterwarnings('ignore')


# We'll download this file using the urlretrieve function from the urllib.request module.
from urllib.request import urlretrieve

urlretrieve('https://covid.ourworldindata.org/data/owid-covid-data.csv','owid-covid-data.csv')

('owid-covid-data.csv', <http.client.HTTPMessage at 0x24fb24d7fd0>)


#Read data from a CSV file into a Pandas DataFrame object
world_covid19_df = pd.read_csv('owid-covid-data.csv')


owidcovidcodebook=pd.read_csv('https://raw.githubusercontent.com/owid/covid-19-data/master/public/data/owid-covid-codebook.csv',index_col=0)


owidcovidcodebook


world_covid19_df


type(world_covid19_df)

pandas.core.frame.DataFrame


#Get the number of rows & columns as a tuple
world_covid19_df.shape

(77070, 59)


#View basic infomation about rows, columns & data types
world_covid19_df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 77070 entries, 0 to 77069
Data columns (total 59 columns):
 #   Column                                 Non-Null Count  Dtype  
---  ------                                 --------------  -----  
 0   iso_code                               77070 non-null  object 
 1   continent                              73292 non-null  object 
 2   location                               77070 non-null  object 
 3   date                                   77070 non-null  object 
 4   total_cases                            75709 non-null  float64
 5   new_cases                              75707 non-null  float64
 6   new_cases_smoothed                     74706 non-null  float64
 7   total_deaths                           66380 non-null  float64
 8   new_deaths                             66538 non-null  float64
 9   new_deaths_smoothed                    74706 non-null  float64
 10  total_cases_per_million                75297 non-null  float64
 11  new_cases_per_million                  75295 non-null  float64
 12  new_cases_smoothed_per_million         74299 non-null  float64
 13  total_deaths_per_million               65981 non-null  float64
 14  new_deaths_per_million                 66139 non-null  float64
 15  new_deaths_smoothed_per_million        74299 non-null  float64
 16  reproduction_rate                      62208 non-null  float64
 17  icu_patients                           7930 non-null   float64
 18  icu_patients_per_million               7930 non-null   float64
 19  hosp_patients                          9550 non-null   float64
 20  hosp_patients_per_million              9550 non-null   float64
 21  weekly_icu_admissions                  697 non-null    float64
 22  weekly_icu_admissions_per_million      697 non-null    float64
 23  weekly_hosp_admissions                 1224 non-null   float64
 24  weekly_hosp_admissions_per_million     1224 non-null   float64
 25  new_tests                              34916 non-null  float64
 26  total_tests                            34687 non-null  float64
 27  total_tests_per_thousand               34687 non-null  float64
 28  new_tests_per_thousand                 34916 non-null  float64
 29  new_tests_smoothed                     39934 non-null  float64
 30  new_tests_smoothed_per_thousand        39934 non-null  float64
 31  positive_rate                          38602 non-null  float64
 32  tests_per_case                         38013 non-null  float64
 33  tests_units                            41281 non-null  object 
 34  total_vaccinations                     5354 non-null   float64
 35  people_vaccinated                      4793 non-null   float64
 36  people_fully_vaccinated                3236 non-null   float64
 37  new_vaccinations                       4565 non-null   float64
 38  new_vaccinations_smoothed              8177 non-null   float64
 39  total_vaccinations_per_hundred         5354 non-null   float64
 40  people_vaccinated_per_hundred          4793 non-null   float64
 41  people_fully_vaccinated_per_hundred    3236 non-null   float64
 42  new_vaccinations_smoothed_per_million  8177 non-null   float64
 43  stringency_index                       66099 non-null  float64
 44  population                             76649 non-null  float64
 45  population_density                     71938 non-null  float64
 46  median_age                             69838 non-null  float64
 47  aged_65_older                          69036 non-null  float64
 48  aged_70_older                          69445 non-null  float64
 49  gdp_per_capita                         70094 non-null  float64
 50  extreme_poverty                        47817 non-null  float64
 51  cardiovasc_death_rate                  70699 non-null  float64
 52  diabetes_prevalence                    71623 non-null  float64
 53  female_smokers                         55533 non-null  float64
 54  male_smokers                           54717 non-null  float64
 55  handwashing_facilities                 35492 non-null  float64
 56  hospital_beds_per_thousand             64664 non-null  float64
 57  life_expectancy                        73234 non-null  float64
 58  human_development_index                70640 non-null  float64
dtypes: float64(54), object(5)
memory usage: 34.7+ MB


# ets first handle numerical features with nan value
Numerical_feat = [feature for feature in world_covid19_df.columns if world_covid19_df[feature].dtypes != 'O']
print('Total numerical features: ', len(Numerical_feat))
print('\nNumerical Features: ', Numerical_feat)

Total numerical features:  54

Numerical Features:  ['total_cases', 'new_cases', 'new_cases_smoothed', 'total_deaths', 'new_deaths', 'new_deaths_smoothed', 'total_cases_per_million', 'new_cases_per_million', 'new_cases_smoothed_per_million', 'total_deaths_per_million', 'new_deaths_per_million', 'new_deaths_smoothed_per_million', 'reproduction_rate', 'icu_patients', 'icu_patients_per_million', 'hosp_patients', 'hosp_patients_per_million', 'weekly_icu_admissions', 'weekly_icu_admissions_per_million', 'weekly_hosp_admissions', 'weekly_hosp_admissions_per_million', 'new_tests', 'total_tests', 'total_tests_per_thousand', 'new_tests_per_thousand', 'new_tests_smoothed', 'new_tests_smoothed_per_thousand', 'positive_rate', 'tests_per_case', 'total_vaccinations', 'people_vaccinated', 'people_fully_vaccinated', 'new_vaccinations', 'new_vaccinations_smoothed', 'total_vaccinations_per_hundred', 'people_vaccinated_per_hundred', 'people_fully_vaccinated_per_hundred', 'new_vaccinations_smoothed_per_million', 'stringency_index', 'population', 'population_density', 'median_age', 'aged_65_older', 'aged_70_older', 'gdp_per_capita', 'extreme_poverty', 'cardiovasc_death_rate', 'diabetes_prevalence', 'female_smokers', 'male_smokers', 'handwashing_facilities', 'hospital_beds_per_thousand', 'life_expectancy', 'human_development_index']


# categorical features
categorical_feat = [feature for feature in world_covid19_df.columns if world_covid19_df[feature].dtypes=='O']
print('Total categorical features: ', len(categorical_feat))
print('\n',categorical_feat)

Total categorical features:  5

 ['iso_code', 'continent', 'location', 'date', 'tests_units']


## Replacing the numerical Missing Values
for feature in Numerical_feat:
    ## We will replace by using median since there are outliers
        world_covid19_df[feature].fillna(0,inplace=True)
    
world_covid19_df[Numerical_feat].isnull().sum()

total_cases                              0
new_cases                                0
new_cases_smoothed                       0
total_deaths                             0
new_deaths                               0
new_deaths_smoothed                      0
total_cases_per_million                  0
new_cases_per_million                    0
new_cases_smoothed_per_million           0
total_deaths_per_million                 0
new_deaths_per_million                   0
new_deaths_smoothed_per_million          0
reproduction_rate                        0
icu_patients                             0
icu_patients_per_million                 0
hosp_patients                            0
hosp_patients_per_million                0
weekly_icu_admissions                    0
weekly_icu_admissions_per_million        0
weekly_hosp_admissions                   0
weekly_hosp_admissions_per_million       0
new_tests                                0
total_tests                              0
total_tests_per_thousand                 0
new_tests_per_thousand                   0
new_tests_smoothed                       0
new_tests_smoothed_per_thousand          0
positive_rate                            0
tests_per_case                           0
total_vaccinations                       0
people_vaccinated                        0
people_fully_vaccinated                  0
new_vaccinations                         0
new_vaccinations_smoothed                0
total_vaccinations_per_hundred           0
people_vaccinated_per_hundred            0
people_fully_vaccinated_per_hundred      0
new_vaccinations_smoothed_per_million    0
stringency_index                         0
population                               0
population_density                       0
median_age                               0
aged_65_older                            0
aged_70_older                            0
gdp_per_capita                           0
extreme_poverty                          0
cardiovasc_death_rate                    0
diabetes_prevalence                      0
female_smokers                           0
male_smokers                             0
handwashing_facilities                   0
hospital_beds_per_thousand               0
life_expectancy                          0
human_development_index                  0
dtype: int64


world_covid19_df


#Store the clean DataFrame in a CSV file
world_covid19_df.to_csv('covid19_df_master.csv',index=False)


covid_df=pd.read_csv('covid19_df_master.csv')
#covid_df.hist(figsize=(15,15));


covid_df.describe().style.background_gradient(cmap="CMRmap_r")


#covid_df['date'] = pd.to_datetime(covid_df.date)


#covid_df['year'] = pd.DatetimeIndex(covid_df.date).year
#covid_df['month'] = pd.DatetimeIndex(covid_df.date).month
#covid_df['day'] = pd.DatetimeIndex(covid_df.date).day
#covid_df['weekday'] = pd.DatetimeIndex(covid_df.date).weekday


covid_df.head(10)


sum(covid_df.duplicated())

0


covid_df.isnull().sum()

iso_code                                     0
continent                                 3778
location                                     0
date                                         0
total_cases                                  0
new_cases                                    0
new_cases_smoothed                           0
total_deaths                                 0
new_deaths                                   0
new_deaths_smoothed                          0
total_cases_per_million                      0
new_cases_per_million                        0
new_cases_smoothed_per_million               0
total_deaths_per_million                     0
new_deaths_per_million                       0
new_deaths_smoothed_per_million              0
reproduction_rate                            0
icu_patients                                 0
icu_patients_per_million                     0
hosp_patients                                0
hosp_patients_per_million                    0
weekly_icu_admissions                        0
weekly_icu_admissions_per_million            0
weekly_hosp_admissions                       0
weekly_hosp_admissions_per_million           0
new_tests                                    0
total_tests                                  0
total_tests_per_thousand                     0
new_tests_per_thousand                       0
new_tests_smoothed                           0
new_tests_smoothed_per_thousand              0
positive_rate                                0
tests_per_case                               0
tests_units                              35789
total_vaccinations                           0
people_vaccinated                            0
people_fully_vaccinated                      0
new_vaccinations                             0
new_vaccinations_smoothed                    0
total_vaccinations_per_hundred               0
people_vaccinated_per_hundred                0
people_fully_vaccinated_per_hundred          0
new_vaccinations_smoothed_per_million        0
stringency_index                             0
population                                   0
population_density                           0
median_age                                   0
aged_65_older                                0
aged_70_older                                0
gdp_per_capita                               0
extreme_poverty                              0
cardiovasc_death_rate                        0
diabetes_prevalence                          0
female_smokers                               0
male_smokers                                 0
handwashing_facilities                       0
hospital_beds_per_thousand                   0
life_expectancy                              0
human_development_index                      0
dtype: int64


covid_df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 77070 entries, 0 to 77069
Data columns (total 59 columns):
 #   Column                                 Non-Null Count  Dtype  
---  ------                                 --------------  -----  
 0   iso_code                               77070 non-null  object 
 1   continent                              73292 non-null  object 
 2   location                               77070 non-null  object 
 3   date                                   77070 non-null  object 
 4   total_cases                            77070 non-null  float64
 5   new_cases                              77070 non-null  float64
 6   new_cases_smoothed                     77070 non-null  float64
 7   total_deaths                           77070 non-null  float64
 8   new_deaths                             77070 non-null  float64
 9   new_deaths_smoothed                    77070 non-null  float64
 10  total_cases_per_million                77070 non-null  float64
 11  new_cases_per_million                  77070 non-null  float64
 12  new_cases_smoothed_per_million         77070 non-null  float64
 13  total_deaths_per_million               77070 non-null  float64
 14  new_deaths_per_million                 77070 non-null  float64
 15  new_deaths_smoothed_per_million        77070 non-null  float64
 16  reproduction_rate                      77070 non-null  float64
 17  icu_patients                           77070 non-null  float64
 18  icu_patients_per_million               77070 non-null  float64
 19  hosp_patients                          77070 non-null  float64
 20  hosp_patients_per_million              77070 non-null  float64
 21  weekly_icu_admissions                  77070 non-null  float64
 22  weekly_icu_admissions_per_million      77070 non-null  float64
 23  weekly_hosp_admissions                 77070 non-null  float64
 24  weekly_hosp_admissions_per_million     77070 non-null  float64
 25  new_tests                              77070 non-null  float64
 26  total_tests                            77070 non-null  float64
 27  total_tests_per_thousand               77070 non-null  float64
 28  new_tests_per_thousand                 77070 non-null  float64
 29  new_tests_smoothed                     77070 non-null  float64
 30  new_tests_smoothed_per_thousand        77070 non-null  float64
 31  positive_rate                          77070 non-null  float64
 32  tests_per_case                         77070 non-null  float64
 33  tests_units                            41281 non-null  object 
 34  total_vaccinations                     77070 non-null  float64
 35  people_vaccinated                      77070 non-null  float64
 36  people_fully_vaccinated                77070 non-null  float64
 37  new_vaccinations                       77070 non-null  float64
 38  new_vaccinations_smoothed              77070 non-null  float64
 39  total_vaccinations_per_hundred         77070 non-null  float64
 40  people_vaccinated_per_hundred          77070 non-null  float64
 41  people_fully_vaccinated_per_hundred    77070 non-null  float64
 42  new_vaccinations_smoothed_per_million  77070 non-null  float64
 43  stringency_index                       77070 non-null  float64
 44  population                             77070 non-null  float64
 45  population_density                     77070 non-null  float64
 46  median_age                             77070 non-null  float64
 47  aged_65_older                          77070 non-null  float64
 48  aged_70_older                          77070 non-null  float64
 49  gdp_per_capita                         77070 non-null  float64
 50  extreme_poverty                        77070 non-null  float64
 51  cardiovasc_death_rate                  77070 non-null  float64
 52  diabetes_prevalence                    77070 non-null  float64
 53  female_smokers                         77070 non-null  float64
 54  male_smokers                           77070 non-null  float64
 55  handwashing_facilities                 77070 non-null  float64
 56  hospital_beds_per_thousand             77070 non-null  float64
 57  life_expectancy                        77070 non-null  float64
 58  human_development_index                77070 non-null  float64
dtypes: float64(54), object(5)
memory usage: 34.7+ MB


covid_df.describe().T.style.background_gradient(cmap="CMRmap_r")


data_popu=covid_df.groupby('continent').sum()


plt.figure(figsize = (20,18)) 
sns.set_style('ticks')
#sum countries population in Asia
plt.subplot(221)
sns.barplot(y='location', x='population', data=covid_df[covid_df['continent'] == 'Asia']).set_title('sum countries population in Asia')

#sum countries population in North America
plt.subplot(222)
sns.barplot(y='location', x='population', data=covid_df[covid_df['continent'] == 'North America']).set_title('sum countries population in North America')

#sum countries population in South America
plt.subplot(223)
sns.barplot(y='location', x='population',data=covid_df[covid_df['continent'] == 'South America']).set_title('sum countries population in South America')

#sum countries population in Europe
plt.subplot(224)
sns.set_style('ticks')
sns.barplot(y='location', x='population', data=covid_df[covid_df['continent'] == 'Europe']).set_title('sum countries population in Europe')
plt.subplots_adjust(left=0.1, 
                    bottom=0.1,  
                    right=0.9,  
                    top=0.9,  
                    wspace=0.4,  
                    hspace=0.2) 
plt.show();


#sum countries population in Africa
plt.figure(figsize = (20,18))
plt.subplot(221)
sns.set_style('ticks')
#sns.set(rc={'figure.figsize':(11.7,8.27)})
sns.barplot(y='location', x='population', data=covid_df[covid_df['continent'] == 'Africa']).set_title('sum countries population in Africa')
#sum countries population in Oceania
plt.subplot(222)
sns.barplot(y='location', x='population', data=covid_df[covid_df['continent'] == 'Oceania']).set_title('sum countries population in Oceania')
plt.subplots_adjust(left=0.1, 
                    bottom=0.1,  
                    right=0.9,  
                    top=0.9,  
                    wspace=0.4,  
                    hspace=0.2) 
plt.show();


#top countries total population in asia
top_popu_asia=covid_df[covid_df['continent'] == 'Asia']
print("The top 10 countries total population in the continent of Asia is :\n",top_popu_asia.groupby(['continent','location'])['population'].max().nlargest(10))

The top 10 countries total population in the continent of Asia is :
 continent  location   
Asia       China          1.439324e+09
           India          1.380004e+09
           Indonesia      2.735236e+08
           Pakistan       2.208923e+08
           Bangladesh     1.646894e+08
           Japan          1.264765e+08
           Philippines    1.095811e+08
           Vietnam        9.733858e+07
           Turkey         8.433907e+07
           Iran           8.399295e+07
Name: population, dtype: float64


#top countries total population in North America
top_popu_north_america=covid_df[covid_df['continent'] == 'North America']
print("The top 10 countries total population in the continent of North America is :\n",top_popu_north_america.groupby(['continent','location'])['population'].max().nlargest(10))

The top 10 countries total population in the continent of North America is :
 continent      location          
North America  United States         331002647.0
               Mexico                128932753.0
               Canada                 37742157.0
               Guatemala              17915567.0
               Haiti                  11402533.0
               Cuba                   11326616.0
               Dominican Republic     10847904.0
               Honduras                9904608.0
               Nicaragua               6624554.0
               El Salvador             6486201.0
Name: population, dtype: float64


#top countries total population in South America
top_popu_south_america=covid_df[covid_df['continent'] == 'South America']
print("The top 10 countries total population in the continent of South America is :\n",top_popu_south_america.groupby(['continent','location'])['population'].max().nlargest(10))

The top 10 countries total population in the continent of South America is :
 continent      location 
South America  Brazil       212559409.0
               Colombia      50882884.0
               Argentina     45195777.0
               Peru          32971846.0
               Venezuela     28435943.0
               Chile         19116209.0
               Ecuador       17643060.0
               Bolivia       11673029.0
               Paraguay       7132530.0
               Uruguay        3473727.0
Name: population, dtype: float64


#top countries total population in Europe
top_popu_europe=covid_df[covid_df['continent'] == 'Europe']
print("The top 10 countries total population in the continent of Europe is :\n",top_popu_europe.groupby(['continent','location'])['population'].max().nlargest(10))

The top 10 countries total population in the continent of Europe is :
 continent  location      
Europe     Russia            145934460.0
           Germany            83783945.0
           France             68147687.0
           United Kingdom     67886004.0
           Italy              60461828.0
           Spain              46754783.0
           Ukraine            43733759.0
           Poland             37846605.0
           Romania            19237682.0
           Netherlands        17134873.0
Name: population, dtype: float64


##Show two or more countries total population numbers the min
data=covid_df[covid_df['continent'] == 'Europe']
data.groupby(['continent','location'])['population'].min().nsmallest(10)

continent  location      
Europe     Vatican              809.0
           Gibraltar          33691.0
           San Marino         33938.0
           Liechtenstein      38137.0
           Monaco             39244.0
           Faeroe Islands     48865.0
           Guernsey           67052.0
           Andorra            77265.0
           Isle of Man        85032.0
           Jersey            101073.0
Name: population, dtype: float64


#top countries total population in Europe
top_popu_africa=covid_df[covid_df['continent'] == 'Africa']
print(" The top 10 countries total population in the continent of Africa is :\n",top_popu_africa.groupby(['continent','location'])['population'].max().nlargest(10))

 The top 10 countries total population in the continent of Africa is :
 continent  location                    
Africa     Nigeria                         206139587.0
           Ethiopia                        114963583.0
           Egypt                           102334403.0
           Democratic Republic of Congo     89561404.0
           Tanzania                         59734213.0
           South Africa                     59308690.0
           Kenya                            53771300.0
           Uganda                           45741000.0
           Algeria                          43851043.0
           Sudan                            43849269.0
Name: population, dtype: float64


#top 10 countries total population in Oceania
top_popu_oceania=covid_df[covid_df['continent'] == 'Oceania']
print(" The top 10 countries total population in the continent of Oceania is :\n",top_popu_oceania.groupby(['continent','location'])['population'].max().nlargest(10))

 The top 10 countries total population in the continent of Oceania is :
 continent  location            
Oceania    Australia               25499881.0
           Papua New Guinea         8947027.0
           New Zealand              4822233.0
           Fiji                      896444.0
           Solomon Islands           686878.0
           Vanuatu                   307150.0
           Samoa                     198410.0
           Micronesia (country)      115021.0
           Marshall Islands           59194.0
Name: population, dtype: float64


continent_populations_df = covid_df.groupby(['continent'])['population'].sum()
continent_populations_df

continent
Africa           5.126297e+11
Asia             1.908886e+12
Europe           3.084160e+11
North America    2.500021e+11
Oceania          1.657967e+10
South America    1.718849e+11
Name: population, dtype: float64


#Show countries in  asia the  total_cases and total_deaths,new_cases,total_tests, numbers mean, and max
data_total=covid_df[covid_df['continent'] == 'Asia']
data_total.groupby(['continent','location']).agg({'total_cases': ['mean','max'],'total_deaths':['mean','max'],'total_tests':['mean','max'],'total_vaccinations':['mean','max']}).style.background_gradient(cmap="CMRmap_r")


#Show countries in  Europe the  total_cases and total_deaths,new_cases,total_tests, numbers mean, and max
data_total=covid_df[covid_df['continent'] == 'Europe']
data_total.groupby(['continent','location']).agg({'total_cases': ['mean','max'],'total_deaths':['mean','max'],'total_tests':['mean','max'],'total_vaccinations':['mean','max']}).style.background_gradient(cmap="CMRmap_r")


#Show countries in  Europe the  total_cases and total_deaths,new_cases,total_tests, numbers mean, and max
data_total=covid_df[covid_df['continent'] == 'North America']
data_total.groupby(['continent','location']).agg({'total_cases': ['mean','max'],'total_deaths':['mean','max'],'total_tests':['mean','max'],'total_vaccinations':['mean','max']}).style.background_gradient(cmap="CMRmap_r")


worldwide_spread=covid_df[["continent","location","total_cases","total_tests","date","total_deaths","positive_rate","total_vaccinations","people_fully_vaccinated"]]

df=worldwide_spread.dropna(axis=0)
df.sort_values("total_tests",ascending=False)
df_loc=df.groupby(['location']).max()
df_loc.drop(["date"],axis=1,inplace=True)
df_loc
for i,r in df_loc.iterrows():
    if r["total_tests"]>0:
        df_loc.loc[i,"test per confirmed(%)"]=(r["total_cases"]/r["total_tests"])*100
df_covid=df_loc.reset_index()  
df_covid.style.background_gradient(cmap="CMRmap_r")


fig = px.choropleth(covid_df, locations="location", 
                    color=np.log(covid_df["total_cases"]),
                    locationmode="country names", hover_name="location", 
                    animation_frame=covid_df["date"],
                    title='Cases over time', color_continuous_scale=px.colors.sequential.matter)
#fig.update(layout_coloraxis_showscale=False)
fig.show()


def plot_map(df, col, pal):
      
    fig = px.choropleth(df, locations="location", locationmode='country names', 
                  color=col, hover_name="location", 
                  title=col, hover_data=[col], color_continuous_scale=pal)
#    fig.update_layout(coloraxis_showscale=False)
    fig.show()


covid_deaths=covid_df[["continent","location","total_cases","date","total_deaths","total_deaths_per_million","total_cases_per_million","total_vaccinations"]]
df=covid_deaths.dropna(axis=0)
df_data=df.groupby(['location']).max()
df_data.drop(["date"],axis=1,inplace=True)
df_data.reset_index(inplace=True)

#df_data.drop(index=171,inplace=True)
df_data
df_data[df_data["continent"]=="Africa"].sum()

location                    AlgeriaAngolaBeninBotswanaBurkina FasoBurundiC...
continent                   AfricaAfricaAfricaAfricaAfricaAfricaAfricaAfri...
total_cases                                                       4.13558e+06
total_deaths                                                           110807
total_deaths_per_million                                              5448.75
total_cases_per_million                                                292485
total_vaccinations                                                9.15029e+06
dtype: object


plot_map(df_data,'total_cases', 'matter')


plot_map(df_data,'total_deaths', 'matter')


plot_map(df_data,'total_deaths_per_million', 'matter')


def plot_hbar(df, col, n, hover_data=[]):
    fig = px.bar(df.sort_values(col).tail(n), 
                 x=col, y="location", color='continent',  
                 text=col, orientation='h', width=700, hover_data=hover_data,
                 color_discrete_sequence = px.colors.qualitative.Dark2)
    fig.update_layout(title=col, xaxis_title="", yaxis_title="", 
                      yaxis_categoryorder = 'total ascending',
                      uniformtext_minsize=8, uniformtext_mode='hide')
    fig.show()


plot_hbar(df_data, 'total_cases', 15)


plot_hbar(df_data, 'total_deaths', 15)


plot_hbar(df_data, 'total_deaths_per_million', 15)


plot_hbar(df_covid, "total_tests", 15)


plot_hbar(df_covid,"total_vaccinations", 15)


plot_hbar(df_covid,"people_fully_vaccinated", 15)


def plot_treemap(col):
    fig = px.treemap(df_data, path=["location"], values=col, height=700,
                 title=col, color_discrete_sequence = px.colors.qualitative.Dark2)
    fig.data[0].textinfo = 'label+text+value'
    fig.show()
def plot_treemap_(col):
    fig = px.treemap(df_covid, path=["location"], values=col, height=700,
                 title=col, color_discrete_sequence = px.colors.qualitative.Dark2)
    fig.data[0].textinfo = 'label+text+value'
    fig.show()


plot_treemap('total_cases')


plot_treemap('total_deaths')


plot_treemap_('total_tests')


plot_treemap_('test per confirmed(%)')


plot_treemap_('total_vaccinations')


plot_treemap_('people_fully_vaccinated')


covid_df['death_rate'] = (covid_df['new_deaths_smoothed_per_million'] / covid_df['new_cases_smoothed_per_million']).replace(np.inf,np.nan)
covid_df['population_coverage'] = covid_df['total_tests'] / covid_df['population']


trace1 = go.Scatter(
    x=covid_df.groupby(['date'])['date'].apply(lambda x: np.unique(x)[0]),
    y=covid_df.groupby(['date'])['new_deaths_smoothed_per_million'].mean(),
        xaxis='x2',
    yaxis='y2',
    name = "mean new deaths smoothed per million"
)
trace2 = go.Scatter(
    x=covid_df.groupby(['date'])['date'].apply(lambda x: np.unique(x)[0]),
    y=covid_df.groupby(['date'])['new_tests_smoothed_per_thousand'].mean(),
    name = "mean new tests smoothed per thousand"
)
trace3 = go.Scatter(
    x=covid_df.groupby(['date'])['date'].apply(lambda x: np.unique(x)[0]),
    y=(covid_df.groupby(['date'])['death_rate'].mean().replace([np.inf],np.nan).interpolate(method='linear', limit_direction='forward', axis=0) * 100).round(3),
    xaxis='x3',
    yaxis='y3',
    name = "interpolated death rate %"
)
trace4 = go.Scatter(
    x=covid_df.groupby(['date'])['date'].apply(lambda x: np.unique(x)[0]),
    y=((covid_df.groupby(['date'])['new_cases_per_million'].apply(lambda x: np.mean(x/1e+6))) * 100).round(6),
    xaxis='x4',
    yaxis='y4',
    name = "mean covid population d2d coverage %"
)

data = [trace1, trace2, trace3, trace4]
layout = go.Layout(
    xaxis=dict(
        domain=[0, 0.45]
    ),
    yaxis=dict(
        domain=[0, 0.45]
    ),
    xaxis2=dict(
        domain=[0.55, 1]
    ),
    xaxis3=dict(
        domain=[0, 0.45],
        anchor='y3'
    ),
    xaxis4=dict(
        domain=[0.55, 1],
        anchor='y4'
    ),
    yaxis2=dict(
        domain=[0, 0.45],
        anchor='x2'
    ),
    yaxis3=dict(
        domain=[0.55, 1]
    ),
    yaxis4=dict(
        domain=[0.55, 1],
        anchor='x4'
    ),
    title = 'Mean new deaths per 1M, new tests per 1K, death rate and covid mean coverage'
)
fig = go.Figure(data=data, layout=layout)
iplot(fig)


def plot_line(col,title):
    trace1 = go.Scatter(
                    x = covid_df[(covid_df['continent']=='Asia')].groupby(['date','continent'])['date'].apply(lambda x: np.unique(x)[0]),
                    y = covid_df[(covid_df['continent']=='Asia')].groupby(['date','continent'])[col].sum(),
                    mode = "lines",
                    name = "Asia",
                    marker = dict(color = 'green'),
    )

    trace2 = go.Scatter(
                        x = covid_df[(covid_df['continent']=='Europe')].groupby(['date','continent'])['date'].apply(lambda x: np.unique(x)[0]),
                        y = covid_df[(covid_df['continent']=='Europe')].groupby(['date','continent'])[col].sum(),
                        mode = "lines",
                        name = "Europe",
                        marker = dict(color = 'red'),
    )

    trace3 = go.Scatter(
                        x = covid_df[(covid_df['continent']=='Africa')].groupby(['date','continent'])['date'].apply(lambda x: np.unique(x)[0]),
                        y = covid_df[(covid_df['continent']=='Africa')].groupby(['date','continent'])[col].sum(),
                        mode = "lines",
                        name = "Africa",
                        marker = dict(color = 'blue'),
                        #text= covid_df.university_name
    )

    trace4 = go.Scatter(
                        x = covid_df[(covid_df['continent']=='North America')].groupby(['date','continent'])['date'].apply(lambda x: np.unique(x)[0]),
                        y = covid_df[(covid_df['continent']=='North America')].groupby(['date','continent'])[col].sum(),
                        mode = "lines",
                        name = "North America",
                        marker = dict(color = 'black'),
    )

    trace5 = go.Scatter(
                        x = covid_df[(covid_df['continent']=='South America')].groupby(['date','continent'])['date'].apply(lambda x: np.unique(x)[0]),
                        y = covid_df[(covid_df['continent']=='South America')].groupby(['date','continent'])[col].sum(),
                        mode = "lines",
                        name = "South America",
                        marker = dict(color = 'brown'),
    )

    data = [trace1,trace2,trace3,trace4,trace5]
    layout = dict(title = title,
                  xaxis= dict(title= "#{} day by day".format(title),ticklen= 5,zeroline= False)
                 )
    fig = dict(data = data, layout = layout)
    iplot(fig)


plot_line('new_deaths_smoothed','New Deaths Smoothed')


plot_line('new_vaccinations_smoothed','new vaccinations smoothed')


plot_line('total_vaccinations','total_vaccinations')


plot_line('new_tests_smoothed','New tests smoothed')


plot_line('positive_rate','positive_rate')


def plot_line_mean(col,title):
    
    
    trace1 = go.Scatter(
                        x = covid_df[(covid_df['continent']=='Asia')&(covid_df['date']>='2020-03-01')].groupby(['date','continent'])['date'].apply(lambda x: np.unique(x)[0]),
                        y = covid_df[(covid_df['continent']=='Asia')&(covid_df['date']>='2020-03-01')].groupby(['date','continent'])[col].mean()*100,
                        mode = "lines",
                        name = "Asia",
                        marker = dict(color = 'green'),
    )

    trace2 = go.Scatter(
                        x = covid_df[(covid_df['continent']=='Europe')&(covid_df['date']>='2020-03-01')].groupby(['date','continent'])['date'].apply(lambda x: np.unique(x)[0]),
                        y = covid_df[(covid_df['continent']=='Europe')&(covid_df['date']>='2020-03-01')].groupby(['date','continent'])[col].mean()*100,
                        mode = "lines",
                        name = "Europe",
                        marker = dict(color = 'red'),
    )

    trace3 = go.Scatter(
                        x = covid_df[(covid_df['continent']=='Africa')&(covid_df['date']>='2020-03-01')].groupby(['date','continent'])['date'].apply(lambda x: np.unique(x)[0]),
                        y = covid_df[(covid_df['continent']=='Africa')&(covid_df['date']>='2020-03-01')].groupby(['date','continent'])[col].mean()*100,
                        mode = "lines",
                        name = "Africa",
                        marker = dict(color = 'blue'),
    )

    trace4 = go.Scatter(
                        x = covid_df[(covid_df['continent']=='North America')&(covid_df['date']>='2020-03-01')].groupby(['date','continent'])['date'].apply(lambda x: np.unique(x)[0]),
                        y = covid_df[(covid_df['continent']=='North America')&(covid_df['date']>='2020-03-01')].groupby(['date','continent'])[col].mean()*100,
                        mode = "lines",
                        name = "North America",
                        marker = dict(color = 'black'),
    )

    trace5 = go.Scatter(
                        x = covid_df[(covid_df['continent']=='South America')&(covid_df['date']>='2020-03-01')].groupby(['date','continent'])['date'].apply(lambda x: np.unique(x)[0]),
                        y = covid_df[(covid_df['continent']=='South America')&(covid_df['date']>='2020-03-01')].groupby(['date','continent'])[col].mean(),
                        mode = "lines",
                        name = "South America",
                        marker = dict(color = 'brown'),
    )

    data = [trace1,trace2,trace3,trace4,trace5]
    layout = dict(title = title,
                  xaxis= dict(title= 'mean deaths/cases %',ticklen= 5,zeroline= False)
                 )
    fig = dict(data = data, layout = layout)
    iplot(fig)


plot_line_mean('death_rate','Mean death rate over continents')


plot_line_mean('population_coverage','Mean population test coverage over continents')


trace1 = go.Scatter(
                    x = covid_df[(covid_df['continent']=='Asia')&(covid_df['date']>='2020-03-01')].groupby(['date','continent'])['date'].apply(lambda x: np.unique(x)[0]),
                    y = covid_df[(covid_df['continent']=='Asia')&(covid_df['date']>='2020-03-01')].groupby(['date','continent'])['death_rate'].mean()*100,
                    mode = "lines",
                    name = "Asia",
                    marker = dict(color = 'green'),
)

trace2 = go.Scatter(
                    x = covid_df[(covid_df['continent']=='Europe')&(covid_df['date']>='2020-03-01')].groupby(['date','continent'])['date'].apply(lambda x: np.unique(x)[0]),
                    y = covid_df[(covid_df['continent']=='Europe')&(covid_df['date']>='2020-03-01')].groupby(['date','continent'])['population_coverage'].mean()*100,
                    mode = "lines",
                    name = "Europe",
                    marker = dict(color = 'red'),
)

trace3 = go.Scatter(
                    x = covid_df[(covid_df['continent']=='Africa')&(covid_df['date']>='2020-03-01')].groupby(['date','continent'])['date'].apply(lambda x: np.unique(x)[0]),
                    y = covid_df[(covid_df['continent']=='Africa')&(covid_df['date']>='2020-03-01')].groupby(['date','continent'])['population_coverage'].mean()*100,
                    mode = "lines",
                    name = "Africa",
                    marker = dict(color = 'blue'),
)

trace4 = go.Scatter(
                    x = covid_df[(covid_df['continent']=='North America')&(covid_df['date']>='2020-03-01')].groupby(['date','continent'])['date'].apply(lambda x: np.unique(x)[0]),
                    y = covid_df[(covid_df['continent']=='North America')&(covid_df['date']>='2020-03-01')].groupby(['date','continent'])['population_coverage'].mean()*100,
                    mode = "lines",
                    name = "North America",
                    marker = dict(color = 'black'),
)

trace5 = go.Scatter(
                    x = covid_df[(covid_df['continent']=='South America')&(covid_df['date']>='2020-03-01')].groupby(['date','continent'])['date'].apply(lambda x: np.unique(x)[0]),
                    y = covid_df[(covid_df['continent']=='South America')&(covid_df['date']>='2020-03-01')].groupby(['date','continent'])['population_coverage'].mean(),
                    mode = "lines",
                    name = "South America",
                    marker = dict(color = 'brown'),
)

data = [trace1,trace2,trace3,trace4,trace5]
layout = dict(title = 'Mean population test coverage over continents',
              xaxis= dict(title= 'mean tests/population %',ticklen= 5,zeroline= False)
             )
fig = dict(data = data, layout = layout)
iplot(fig)


covid_df_grouped = covid_df.groupby(['location','continent']).agg({'new_deaths': np.sum, 'gdp_per_capita': np.mean, 'new_cases':np.sum}).reset_index()
covid_df_grouped = covid_df_grouped[(~covid_df_grouped['new_deaths'].isnull())&(~covid_df_grouped['new_cases'].isnull())&(~covid_df_grouped['gdp_per_capita'].isnull())&(~covid_df_grouped['continent'].isnull())]


fig = px.scatter(covid_df_grouped, 
                 x="new_deaths", y="gdp_per_capita", size="new_cases", color="continent",
                 hover_name="location", log_x=True, size_max=60)
fig.show()


covid_df_grouped = covid_df.groupby(['location','continent']).agg({'handwashing_facilities': np.mean, 'new_deaths_smoothed_per_million': np.sum, 'extreme_poverty':np.mean}).reset_index()
covid_df_grouped = covid_df_grouped[(~covid_df_grouped['handwashing_facilities'].isnull())&(~covid_df_grouped['new_deaths_smoothed_per_million'].isnull())&(~covid_df_grouped['extreme_poverty'].isnull())&(~covid_df_grouped['continent'].isnull())]


fig = px.scatter(covid_df_grouped, 
                 x="new_deaths_smoothed_per_million", y="handwashing_facilities", size="extreme_poverty", color="continent",
                 hover_name="location", log_x=True, size_max=60)
fig.show()


covid_df_grouped = covid_df.groupby(['location','continent']).agg({'population_density': np.mean, 'new_deaths_smoothed_per_million': np.sum, 'aged_70_older':np.mean}).reset_index()
covid_df_grouped = covid_df_grouped[(~covid_df_grouped['population_density'].isnull())&(~covid_df_grouped['new_deaths_smoothed_per_million'].isnull())&(~covid_df_grouped['aged_70_older'].isnull())&(~covid_df_grouped['continent'].isnull())]


fig = px.scatter(covid_df_grouped, 
                 x="new_deaths_smoothed_per_million", y="aged_70_older", size="population_density", color="continent",
                 hover_name="location", log_x=True, size_max=60)
fig.show()


covid_df_grouped = covid_df.groupby(['location','continent']).agg({'life_expectancy': np.mean, 'new_deaths_smoothed_per_million': np.sum, 'hospital_beds_per_thousand':np.mean}).reset_index()
covid_df_grouped = covid_df_grouped[(~covid_df_grouped['life_expectancy'].isnull())&(~covid_df_grouped['new_deaths_smoothed_per_million'].isnull())&(~covid_df_grouped['hospital_beds_per_thousand'].isnull())&(~covid_df_grouped['continent'].isnull())]


fig = px.scatter(covid_df_grouped, 
                 x="new_deaths_smoothed_per_million", y="life_expectancy", size="hospital_beds_per_thousand", color="continent",
                 hover_name="location", log_x=True, size_max=60)
fig.show()


covid_df_grouped = covid_df.groupby(['location','continent']).agg({'death_rate': np.mean, 'stringency_index': np.mean, 'new_cases':np.sum}).reset_index()
covid_df_grouped = covid_df_grouped[(~covid_df_grouped['death_rate'].isnull())&(~covid_df_grouped['stringency_index'].isnull())&(~covid_df_grouped['new_cases'].isnull())&(~covid_df_grouped['continent'].isnull())]


fig = px.scatter(covid_df_grouped, 
                 x="death_rate", y="stringency_index", size="new_cases", color="continent",
                 hover_name="location", log_x=True, size_max=60)
fig.show()


covid_df_copy = world_covid19_df.copy()


covid_df_copy = covid_df.copy()


covid_df_copy.head(10)


correlations = covid_df_copy.corr()['total_cases'].abs().sort_values(ascending=False).drop('total_cases',axis=0).to_frame()
correlations.plot(kind='bar',figsize=(12,10));


# Function to see the correlation of each features

def corr(df):
    "argument df tp get the correlation for"
    return df.corr()


corr(covid_df_copy).style.background_gradient(cmap="CMRmap_r")


#owid_covid_data = pd.read_csv('https://raw.githubusercontent.com/owid/covid-19-data/master/public/data/owid-covid-data.csv')
#owid_covid_data.head()


#Select Coloumn to clean
ColumnToClean = ['total_cases', 'new_cases', 'total_deaths', 'new_deaths','aged_65_older','aged_70_older','gdp_per_capita','diabetes_prevalence','female_smokers','male_smokers','hospital_beds_per_thousand']
#Replace the nan with emty string
covid_df_copy[['location']] = covid_df_copy[['location']].fillna('')
#Replace the Nan with 0
covid_df_copy[ColumnToClean] = covid_df_copy[ColumnToClean].fillna(0)
#Filter the data so we will get only overall world data
covid_df_copy = covid_df_copy.query('location=="World"' )
Data_For_Regression = pd.DataFrame(columns=['date','total_cases', 'new_cases', 'total_deaths', 'new_deaths','aged_65_older','aged_70_older','gdp_per_capita','diabetes_prevalence','female_smokers','male_smokers','hospital_beds_per_thousand'], data=covid_df_copy[['date','total_cases', 'new_cases', 'total_deaths', 'new_deaths','aged_65_older','aged_70_older','gdp_per_capita','diabetes_prevalence','female_smokers','male_smokers','hospital_beds_per_thousand']].values)
Data_For_Regression.head()


#set the index as date
Data_For_Regression['date'] = pd.to_datetime(Data_For_Regression['date'])
Data_For_Regression = Data_For_Regression.set_index('date')
Data_For_Regression.head()


#Plot the graph
Data_For_Regression['total_cases'].plot(figsize=(15,6), color="green")
plt.legend(loc=4)
plt.xlabel('Date')
plt.ylabel('Cases')
plt.show()

Data_For_Regression['total_deaths'].plot(figsize=(15,6), color="red")
plt.xlabel('Date')
plt.ylabel('Death')
plt.show()

Data_For_Regression['new_cases'].plot(figsize=(15,6), color="blue")
plt.xlabel('Date')
plt.ylabel('New Cases')
plt.show()


# pick total death as forecast column
forecast_col = 'total_deaths'

# Chosing 30 days as number of forecast days
forecast_out = int(30)
print('length =',len(Data_For_Regression), "and forecast_out =", forecast_out)

length = 428 and forecast_out = 30


# Creating label by shifting 'total_deaths' according to 'forecast_out'
Data_For_Regression['temp'] = Data_For_Regression[forecast_col].shift(-forecast_out)
print(Data_For_Regression.head(2))
print('\n')
# verify rows with NAN in Label column 
print(Data_For_Regression.tail(2))

           total_cases new_cases total_deaths new_deaths aged_65_older  \
date                                                                     
2020-01-22         557         0           17          0         8.696   
2020-01-23         655        98           18          1         8.696   

           aged_70_older gdp_per_capita diabetes_prevalence female_smokers  \
date                                                                         
2020-01-22         5.355        15469.2                8.51          6.434   
2020-01-23         5.355        15469.2                8.51          6.434   

           male_smokers hospital_beds_per_thousand  temp  
date                                                      
2020-01-22       34.635                      2.705  2252  
2020-01-23       34.635                      2.705  2459  


            total_cases new_cases total_deaths new_deaths aged_65_older  \
date                                                                      
2021-03-23  1.24205e+08    514125  2.73408e+06      11131         8.696   
2021-03-24  1.24777e+08    572494  2.74352e+06       9437         8.696   

           aged_70_older gdp_per_capita diabetes_prevalence female_smokers  \
date                                                                         
2021-03-23         5.355        15469.2                8.51          6.434   
2021-03-24         5.355        15469.2                8.51          6.434   

           male_smokers hospital_beds_per_thousand temp  
date                                                     
2021-03-23       34.635                      2.705  NaN  
2021-03-24       34.635                      2.705  NaN


# Define features Matrix X by excluding the label column which we just created 
X = np.array(Data_For_Regression.drop(['temp'], 1))

# Using a feature in sklearn, preposessing to scale features
X = preprocessing.scale(X)
print(X[1,:])

[-0.9663012  -1.31650812 -1.17784139 -1.57843638  0.          0.
  0.          0.          0.          0.          0.        ]


# X contains last 'n= forecast_out' rows for which we don't have label data
# Put those rows in different Matrix X_forecast_out by X_forecast_out = X[end-forecast_out:end]

X_forecast_out = X[-forecast_out:]
X = X[:-forecast_out]
print ("Length of X_forecast_out:", len(X_forecast_out), "& Length of X :", len(X))

Length of X_forecast_out: 30 & Length of X : 398


# Define vector y for the data we have prediction for
# make sure length of X and y are identical
y = np.array(Data_For_Regression['temp'])
y = y[:-forecast_out]
print('Length of y: ',len(y))

Length of y:  398


# (split into test and train data)
# test_size = 0.2 ==> 20% data is test data
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=0)
print('length of X_train and x_test: ', len(X_train), len(X_test))

length of X_train and x_test:  318 80


# Create linear regression object
lr = LinearRegression()

# Train the model using the training sets
lr.fit(X_train, y_train)
# Test
accuracy = lr.score(X_test, y_test)
print("Accuracy of Linear Regression: ", accuracy)

Accuracy of Linear Regression:  0.9973696543474295


# Predict using our Model
forecast_prediction = lr.predict(X_forecast_out)
print(forecast_prediction)

[2778934.74331843 2811657.84071672 2812261.31279776 2822597.97962693
 2803505.31207952 2769463.37363849 2787605.79840336 2816668.56341012
 2869000.24029423 2875403.53353488 2885040.20016288 2870688.23543137
 2850066.28688718 2845559.87957909 2906341.32547695 2929596.88719754
 2942844.46983477 2955475.10544147 2949527.89272841 2910550.93070793
 2921418.41535896 2984009.67513252 3014484.13111027 3031947.56060694
 3031960.60026221 3022250.13987609 2984223.43115581 3028500.69362795
 3068012.28187795 3085489.79902353]


Data_For_Regression.tail()


last_date = Data_For_Regression.iloc[-1].name 
last_date

Timestamp('2021-03-24 00:00:00')


todays_date = datetime.strptime(last_date.strftime("%Y-%m-%d"), "%Y-%m-%d")
todays_date = todays_date + timedelta(days=1)
todays_date = datetime.strptime(todays_date.strftime("%Y-%m-%d"), "%Y-%m-%d")
index = pd.date_range(todays_date, periods=30, freq='D')
columns = ['total_cases', 'new_cases', 'total_deaths', 'new_deaths','aged_65_older','aged_70_older','gdp_per_capita','diabetes_prevalence','female_smokers','male_smokers','hospital_beds_per_thousand','temp','forecast']
temp_df = pd.DataFrame(index=index, columns=columns)
temp_df


j=0
for i in forecast_prediction:
    temp_df.iat[j,12] = i
    j= j+1

temp_df


#Append the forcasted - Initially did it for easness but kater decided to use xgboost also
Data_For_Regression['total_deaths'].plot(figsize=(15,6), color="red")
temp_df['forecast'].plot(figsize=(15,6), color="orange")
plt.xlabel('Date')
plt.ylabel('Death')
plt.show()


#  XGboost algorithm to see if we can get better results
xgb_model = xgb.XGBRegressor(objective ='reg:squarederror',colsample_bytree=0.4,
                 gamma=0,                 
                 learning_rate=0.07,
                 max_depth=3,
                 min_child_weight=1.5,
                 n_estimators=10000,                                                                    
                 reg_alpha=0.75,
                 reg_lambda=0.45,
                 subsample=0.6) 

traindf, testdf = train_test_split(X_train, test_size = 0.2)

xgb_model.fit(X_train,y_train)

xgforecast_prediction = xgb_model.predict(X_forecast_out)

xgforecast_prediction

array([2723255.2, 2710872.5, 2699675.5, 2701513.2, 2716340. , 2640903.8,
       2696406. , 2713487.2, 2721652.2, 2719421. , 2699927. , 2723408. ,
       2636880. , 2680294.5, 2722915.8, 2692492.5, 2714138.8, 2676936.8,
       2660933. , 2603629.5, 2627927.8, 2695879.8, 2677862.8, 2673236.2,
       2680948. , 2619059.5, 2632421.8, 2690095. , 2688020.8, 2661255. ],
      dtype=float32)


#Setting the temperory df with XGboost forecasted data
j=0
for i in xgforecast_prediction:
    temp_df.iat[j,12] = i
    j= j+1


Data_For_Regression['total_deaths'].plot(figsize=(15,6), color="red")
temp_df['forecast'].plot(figsize=(15,6), color="orange")
plt.xlabel('Date')
plt.ylabel('Death')
plt.show()


covid_df_copy = covid_df.copy()


covid_df_copy.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 77070 entries, 0 to 77069
Data columns (total 61 columns):
 #   Column                                 Non-Null Count  Dtype  
---  ------                                 --------------  -----  
 0   iso_code                               77070 non-null  object 
 1   continent                              73292 non-null  object 
 2   location                               77070 non-null  object 
 3   date                                   77070 non-null  object 
 4   total_cases                            77070 non-null  float64
 5   new_cases                              77070 non-null  float64
 6   new_cases_smoothed                     77070 non-null  float64
 7   total_deaths                           77070 non-null  float64
 8   new_deaths                             77070 non-null  float64
 9   new_deaths_smoothed                    77070 non-null  float64
 10  total_cases_per_million                77070 non-null  float64
 11  new_cases_per_million                  77070 non-null  float64
 12  new_cases_smoothed_per_million         77070 non-null  float64
 13  total_deaths_per_million               77070 non-null  float64
 14  new_deaths_per_million                 77070 non-null  float64
 15  new_deaths_smoothed_per_million        77070 non-null  float64
 16  reproduction_rate                      77070 non-null  float64
 17  icu_patients                           77070 non-null  float64
 18  icu_patients_per_million               77070 non-null  float64
 19  hosp_patients                          77070 non-null  float64
 20  hosp_patients_per_million              77070 non-null  float64
 21  weekly_icu_admissions                  77070 non-null  float64
 22  weekly_icu_admissions_per_million      77070 non-null  float64
 23  weekly_hosp_admissions                 77070 non-null  float64
 24  weekly_hosp_admissions_per_million     77070 non-null  float64
 25  new_tests                              77070 non-null  float64
 26  total_tests                            77070 non-null  float64
 27  total_tests_per_thousand               77070 non-null  float64
 28  new_tests_per_thousand                 77070 non-null  float64
 29  new_tests_smoothed                     77070 non-null  float64
 30  new_tests_smoothed_per_thousand        77070 non-null  float64
 31  positive_rate                          77070 non-null  float64
 32  tests_per_case                         77070 non-null  float64
 33  tests_units                            41281 non-null  object 
 34  total_vaccinations                     77070 non-null  float64
 35  people_vaccinated                      77070 non-null  float64
 36  people_fully_vaccinated                77070 non-null  float64
 37  new_vaccinations                       77070 non-null  float64
 38  new_vaccinations_smoothed              77070 non-null  float64
 39  total_vaccinations_per_hundred         77070 non-null  float64
 40  people_vaccinated_per_hundred          77070 non-null  float64
 41  people_fully_vaccinated_per_hundred    77070 non-null  float64
 42  new_vaccinations_smoothed_per_million  77070 non-null  float64
 43  stringency_index                       77070 non-null  float64
 44  population                             77070 non-null  float64
 45  population_density                     77070 non-null  float64
 46  median_age                             77070 non-null  float64
 47  aged_65_older                          77070 non-null  float64
 48  aged_70_older                          77070 non-null  float64
 49  gdp_per_capita                         77070 non-null  float64
 50  extreme_poverty                        77070 non-null  float64
 51  cardiovasc_death_rate                  77070 non-null  float64
 52  diabetes_prevalence                    77070 non-null  float64
 53  female_smokers                         77070 non-null  float64
 54  male_smokers                           77070 non-null  float64
 55  handwashing_facilities                 77070 non-null  float64
 56  hospital_beds_per_thousand             77070 non-null  float64
 57  life_expectancy                        77070 non-null  float64
 58  human_development_index                77070 non-null  float64
 59  death_rate                             69646 non-null  float64
 60  population_coverage                    76649 non-null  float64
dtypes: float64(56), object(5)
memory usage: 35.9+ MB


#it decided to Create a column the High Risk and base it off of total_deaths_per_million which is the Total deaths attributed to COVID-19 per 1,000,000 people
covid_df_copy['HighRisk'] = zscore(covid_df_copy['total_deaths_per_million']) > 0.65


covid_df_copy.head(20)


corr = covid_df_copy[['death_rate', 'total_deaths_per_million', 'aged_65_older','extreme_poverty', 'icu_patients', 'life_expectancy', 'cardiovasc_death_rate', 'diabetes_prevalence', 'human_development_index', 'population_density', 'aged_70_older', 'population_coverage']].corr()
corr.style.background_gradient(cmap='coolwarm')
#Total deaths attributed to COVID-19 per 1,000,000 people
#With the new data the correlations seem stronger on aged_70_older, 'cardiovasc_death_rate', 'diabetes_prevalence', 'human_development_index', 'population_density', 'aged_70_older',and  'population_coverage' than before.


predictors = ['diabetes_prevalence','icu_patients','life_expectancy', 'cardiovasc_death_rate', 'human_development_index', 'aged_70_older', 'population_density', 'female_smokers', 'male_smokers', 'extreme_poverty']
target = 'HighRisk'
X = covid_df_copy[predictors].values
y = covid_df_copy[target].values

# Split the data into training and test sets, and scale
scaler = StandardScaler()

# unscaled version (note that scaling is only used on predictor variables)
X_train_raw, X_test_raw, y_train, y_test = train_test_split(X, y, test_size=0.30, random_state=42)

# scaled version
X_train = scaler.fit_transform(X_train_raw)
X_test = scaler.transform(X_test_raw)
print('First 10 Rows of Scaled Data: \n\n', X_train[0:10:,], '\n')

knn = KNeighborsClassifier()
knn.fit(X_train, y_train)
predictions = knn.predict(X_test)
accuracy = (predictions == y_test).mean()
print('Accuracy:', round(accuracy * 100, 2), '%')

First 10 Rows of Scaled Data: 

 [[-1.22169566e-01 -1.00003174e-01  4.19810806e-01  3.16293779e-01
   3.25666302e-01 -2.68176903e-01 -1.87368846e-01 -6.89139991e-01
   3.82352074e-01 -4.55583592e-01]
 [-3.37900153e-02 -1.00003174e-01  1.09646599e-01  1.49829377e+00
   1.19058990e-01 -4.90621258e-01 -1.77899529e-01 -4.00766930e-01
   1.45987921e+00 -4.02647313e-01]
 [ 8.07398219e-03 -1.00003174e-01  4.57510323e-01  3.88075004e-01
   7.79392163e-01  9.43289275e-01 -1.26843579e-01  1.53829331e+00
   7.73692775e-01 -4.43819974e-01]
 [-4.03588660e-01 -1.00003174e-01 -3.08475315e-01 -2.67112893e-01
   1.67672475e-01 -4.51607940e-01 -1.68786616e-01  4.67085097e-02
   5.32455357e-01  6.26669230e-01]
 [ 1.37563123e+00 -1.00003174e-01  2.50734185e-01 -9.79981515e-04
   5.93040470e-01  3.82259364e-02 -1.73372457e-01 -4.50486423e-01
  -1.53731078e-01 -4.84992636e-01]
 [-2.50087336e-01 -1.00003174e-01  1.74192741e-01  1.46040196e+00
   6.33551708e-01  9.94850736e-01 -1.92755961e-01  1.56812500e+00
   1.87802407e+00 -4.79110827e-01]
 [-1.28580166e-02 -1.00003174e-01 -1.74813392e-01  1.78663848e-01
   1.43365732e-01 -4.69175340e-01 -1.93365131e-01 -7.58747281e-01
  -1.24734071e+00 -2.85011136e-01]
 [-4.52429991e-01 -1.00003174e-01  7.35115856e-01 -9.10966912e-01
   1.17235117e+00  1.31882098e+00 -1.89192566e-01  1.19025686e+00
  -1.37648583e-01 -4.73229018e-01]
 [-3.96611327e-01 -1.00003174e-01  4.27236468e-01 -7.15470616e-01
   3.70228663e-01 -1.31059921e-01 -1.56031317e-01 -5.59869308e-01
  -5.87958431e-01 -2.73247519e-01]
 [ 7.38368161e-01 -1.00003174e-01  1.93042500e-01  7.91329131e-01
   2.28439332e-01 -5.05679029e-01 -1.96041943e-01 -7.58747281e-01
  -1.24734071e+00 -4.84992636e-01]] 

Accuracy: 90.2 %


n = 8
accuracies = []
ks = np.arange(1, n+1, 2)
for k in ks:
    print(k, ' ', end='')
    knn = KNeighborsClassifier(n_neighbors=k)
    knn.fit(X_train, y_train)
    predictions = knn.predict(X_test)
    acc = (predictions == y_test).mean()
    accuracies.append(acc)
print('done')

def get_best(ks, accuracies):
    maximum = np.array(accuracies).max()
    indexMax = np.where(accuracies == maximum)
    return ks[indexMax], maximum

best_k, best_acc = get_best(ks, accuracies)
print('best k = {}, best accuracy: {:0.3f}%'.format(best_k, best_acc * 100))

1  3  5  7  done
best k = [5], best accuracy: 90.195%


print('Comparison of predictions to y_test values: \n\n', predictions == y_test)
print('\nPredictions:\n\n', predictions)
print('\nY_test values:\n\n', y_test)

Comparison of predictions to y_test values: 

 [ True  True  True ...  True False  True]

Predictions:

 [False False False ...  True False False]

Y_test values:

 [False False False ...  True  True False]


predictors = ['diabetes_prevalence','icu_patients','life_expectancy', 'cardiovasc_death_rate','human_development_index', 'aged_70_older', 'population_density', 'female_smokers', 'male_smokers', 'extreme_poverty']
target = 'HighRisk'
X = covid_df_copy[predictors].values
y = covid_df_copy[target].values
# Split the data into training and test sets, and scale
scaler = StandardScaler()

# unscaled version (note that scaling is only used on predictor variables)
X_train_raw, X_test_raw, y_train, y_test = train_test_split(X, y, test_size=0.30, random_state=42)

# scaled version
X_train = scaler.fit_transform(X_train_raw)
X_test = scaler.transform(X_test_raw)

ks = np.arange(1, 8, 2)
for k in ks:
    best_acc = 0
    selected = []
    remaining = list(range(X_train.shape[1]))
    n = 11
    better = True
    while len(selected) < n and better == True:
        # find the single features that works best in conjunction
        # with the already selected features
        acc_max = 0
        for i in remaining:
            # make a version of the training data with just selected, feature i
            selectedFi = selected.copy()
            selectedFi.append(i)
            X_si = X_train[:,selectedFi]
            y_siTrain = y_train[~np.isnan(X_si).any(axis=1)]
            X_si=X_si[~np.isnan(X_si).any(axis=1)]
            knn = KNeighborsClassifier(n_neighbors=k)
            knn.fit(X_si, y_siTrain)
            X_testSi = X_test[:,selectedFi]
            y_siTest = y_test[~np.isnan(X_testSi).any(axis=1)]
            X_testSi = X_testSi[~np.isnan(X_testSi).any(axis=1)]
            predictions = knn.predict(X_testSi)

            acc = (predictions == y_siTest).mean()
            if (acc > acc_max):
                acc_max = acc
                i_min = i
                if (best_acc < acc):
                    best_acc = acc
                    better = True
                else:
                    better = False


        if (better == True):        
            remaining.remove(i_min)
            selected.append(i_min)
            print('k: {}; num features: {}; features: {}; bestAcc: {:.2f}%'.format(k, len(selected), [predictors[x] for x in selected], best_acc*100))

k: 1; num features: 1; features: ['aged_70_older']; bestAcc: 87.95%
k: 3; num features: 1; features: ['diabetes_prevalence']; bestAcc: 87.82%
k: 3; num features: 2; features: ['diabetes_prevalence', 'icu_patients']; bestAcc: 89.25%
k: 3; num features: 3; features: ['diabetes_prevalence', 'icu_patients', 'life_expectancy']; bestAcc: 90.27%
k: 3; num features: 4; features: ['diabetes_prevalence', 'icu_patients', 'life_expectancy', 'cardiovasc_death_rate']; bestAcc: 90.28%
k: 5; num features: 1; features: ['diabetes_prevalence']; bestAcc: 87.86%
k: 5; num features: 2; features: ['diabetes_prevalence', 'icu_patients']; bestAcc: 89.51%
k: 5; num features: 3; features: ['diabetes_prevalence', 'icu_patients', 'male_smokers']; bestAcc: 90.29%
k: 5; num features: 4; features: ['diabetes_prevalence', 'icu_patients', 'male_smokers', 'life_expectancy']; bestAcc: 90.43%
k: 5; num features: 5; features: ['diabetes_prevalence', 'icu_patients', 'male_smokers', 'life_expectancy', 'female_smokers']; bestAcc: 90.52%
k: 5; num features: 6; features: ['diabetes_prevalence', 'icu_patients', 'male_smokers', 'life_expectancy', 'female_smokers', 'aged_70_older']; bestAcc: 90.71%
k: 5; num features: 7; features: ['diabetes_prevalence', 'icu_patients', 'male_smokers', 'life_expectancy', 'female_smokers', 'aged_70_older', 'extreme_poverty']; bestAcc: 90.83%
k: 7; num features: 1; features: ['female_smokers']; bestAcc: 88.10%
k: 7; num features: 2; features: ['female_smokers', 'icu_patients']; bestAcc: 89.65%
k: 7; num features: 3; features: ['female_smokers', 'icu_patients', 'life_expectancy']; bestAcc: 90.38%
k: 7; num features: 4; features: ['female_smokers', 'icu_patients', 'life_expectancy', 'population_density']; bestAcc: 90.39%
k: 7; num features: 5; features: ['female_smokers', 'icu_patients', 'life_expectancy', 'population_density', 'aged_70_older']; bestAcc: 90.90%


# change default plot size
rcParams['figure.figsize'] = 10,8
sns.scatterplot(data=covid_df_copy, x='male_smokers', y='cardiovasc_death_rate', hue='HighRisk', style='HighRisk');
plt.xlabel("Cardiovascular Death Rate")
plt.ylabel("Male Smokers");


sns.scatterplot(data=covid_df_copy, x='life_expectancy', y='diabetes_prevalence', hue='HighRisk', style='HighRisk')
plt.xlabel("Life Expectancy")
plt.ylabel("% of Obesity");


sns.scatterplot(data=covid_df_copy, x='human_development_index', y='positive_rate', hue='HighRisk', style='HighRisk');
plt.xlabel("Human Development Index")
plt.ylabel("positive_rate");


sns.scatterplot(data=covid_df_copy, x='aged_65_older', y='diabetes_prevalence', hue='HighRisk', style='HighRisk');
plt.xlabel("% Age 65 and older")
plt.ylabel("% of diabetes_prevalence");


k = 7
predictors = ['diabetes_prevalence','icu_patients','female_smokers','male_smokers', 'human_development_index', 'life_expectancy','cardiovasc_death_rate','positive_rate']
target = 'HighRisk'

# unscaled version (note that scaling is only used on predictor variables)
X = covid_df_copy[predictors].values
y = covid_df_copy[target].values

# Split the data into training and test sets, and scale
scaler = StandardScaler()

X_train_raw, X_test_raw, y_train, y_test = train_test_split(X, y, test_size=0.30, random_state=42)
# scaled version
X_train = scaler.fit_transform(X_train_raw)
X_test = scaler.transform(X_test_raw)

#Remove data rows with nan
y_train = y_train[~np.isnan(X_train).any(axis=1)]
X_train = X_train[~np.isnan(X_train).any(axis=1)]

y_test = y_test[~np.isnan(X_test).any(axis=1)]
X_test = X_test[~np.isnan(X_test).any(axis=1)]

knn = KNeighborsClassifier(n_neighbors=k)
knn.fit(X_train, y_train)
predictions = knn.predict(X_test)

acc = (predictions == y_test).mean()

print('Comparison of predictions to y_test values: \n\n', predictions == y_test)
print('\nPredictions:\n\n', predictions)
print('\nY_test values:\n\n', y_test)

print('\nAccurancy: ', acc)

Comparison of predictions to y_test values: 

 [ True  True  True ...  True False  True]

Predictions:

 [False False False ...  True False False]

Y_test values:

 [False False False ...  True  True False]

Accurancy:  0.9352536654988971

	source	description
column
iso_code	International Organization for Standardization	ISO 3166-1 alpha-3 – three-letter country codes
continent	Our World in Data	Continent of the geographical location
location	Our World in Data	Geographical location
date	Our World in Data	Date of observation
total_cases	COVID-19 Data Repository by the Center for Sys...	Total confirmed cases of COVID-19
new_cases	COVID-19 Data Repository by the Center for Sys...	New confirmed cases of COVID-19
new_cases_smoothed	COVID-19 Data Repository by the Center for Sys...	New confirmed cases of COVID-19 (7-day smoothed)
total_deaths	COVID-19 Data Repository by the Center for Sys...	Total deaths attributed to COVID-19
new_deaths	COVID-19 Data Repository by the Center for Sys...	New deaths attributed to COVID-19
new_deaths_smoothed	COVID-19 Data Repository by the Center for Sys...	New deaths attributed to COVID-19 (7-day smoot...
total_cases_per_million	COVID-19 Data Repository by the Center for Sys...	Total confirmed cases of COVID-19 per 1,000,00...
new_cases_per_million	COVID-19 Data Repository by the Center for Sys...	New confirmed cases of COVID-19 per 1,000,000 ...
new_cases_smoothed_per_million	COVID-19 Data Repository by the Center for Sys...	New confirmed cases of COVID-19 (7-day smoothe...
total_deaths_per_million	COVID-19 Data Repository by the Center for Sys...	Total deaths attributed to COVID-19 per 1,000,...
new_deaths_per_million	COVID-19 Data Repository by the Center for Sys...	New deaths attributed to COVID-19 per 1,000,00...
new_deaths_smoothed_per_million	COVID-19 Data Repository by the Center for Sys...	New deaths attributed to COVID-19 (7-day smoot...
reproduction_rate	Arroyo Marioli et al. (2020). https://doi.org/...	Real-time estimate of the effective reproducti...
icu_patients	European CDC for European countries / UK Gover...	Number of COVID-19 patients in intensive care ...
icu_patients_per_million	European CDC for European countries / UK Gover...	Number of COVID-19 patients in intensive care ...
hosp_patients	European CDC for European countries / UK Gover...	Number of COVID-19 patients in hospital on a g...
hosp_patients_per_million	European CDC for European countries / UK Gover...	Number of COVID-19 patients in hospital on a g...
weekly_icu_admissions	European CDC for European countries / UK Gover...	Number of COVID-19 patients newly admitted to ...
weekly_icu_admissions_per_million	European CDC for European countries / UK Gover...	Number of COVID-19 patients newly admitted to ...
weekly_hosp_admissions	European CDC for European countries / UK Gover...	Number of COVID-19 patients newly admitted to ...
weekly_hosp_admissions_per_million	European CDC for European countries / UK Gover...	Number of COVID-19 patients newly admitted to ...
total_tests	National government reports	Total tests for COVID-19
new_tests	National government reports	New tests for COVID-19 (only calculated for co...
total_tests_per_thousand	National government reports	Total tests for COVID-19 per 1,000 people
new_tests_per_thousand	National government reports	New tests for COVID-19 per 1,000 people
new_tests_smoothed	National government reports	New tests for COVID-19 (7-day smoothed). For c...
new_tests_smoothed_per_thousand	National government reports	New tests for COVID-19 (7-day smoothed) per 1,...
positive_rate	National government reports	The share of COVID-19 tests that are positive,...
tests_per_case	National government reports	Tests conducted per new confirmed case of COVI...
tests_units	National government reports	Units used by the location to report its testi...
total_vaccinations	National government reports	Total number of COVID-19 vaccination doses adm...
people_vaccinated	National government reports	Total number of people who received at least o...
people_fully_vaccinated	National government reports	Total number of people who received all doses ...
new_vaccinations	National government reports	New COVID-19 vaccination doses administered (o...
new_vaccinations_smoothed	National government reports	New COVID-19 vaccination doses administered (7...
total_vaccinations_per_hundred	National government reports	Total number of COVID-19 vaccination doses adm...
people_vaccinated_per_hundred	National government reports	Total number of people who received at least o...
people_fully_vaccinated_per_hundred	National government reports	Total number of people who received all doses ...
new_vaccinations_smoothed_per_million	National government reports	New COVID-19 vaccination doses administered (7...
stringency_index	Oxford COVID-19 Government Response Tracker, B...	Government Response Stringency Index: composit...
population	United Nations, Department of Economic and Soc...	Population in 2020
population_density	World Bank World Development Indicators, sourc...	Number of people divided by land area, measure...
median_age	UN Population Division, World Population Prosp...	Median age of the population, UN projection fo...
aged_65_older	World Bank World Development Indicators based ...	Share of the population that is 65 years and o...
aged_70_older	United Nations, Department of Economic and Soc...	Share of the population that is 70 years and o...
gdp_per_capita	World Bank World Development Indicators, sourc...	Gross domestic product at purchasing power par...
extreme_poverty	World Bank World Development Indicators, sourc...	Share of the population living in extreme pove...
cardiovasc_death_rate	Global Burden of Disease Collaborative Network...	Death rate from cardiovascular disease in 2017...
diabetes_prevalence	World Bank World Development Indicators, sourc...	Diabetes prevalence (% of population aged 20 t...
female_smokers	World Bank World Development Indicators, sourc...	Share of women who smoke, most recent year ava...
male_smokers	World Bank World Development Indicators, sourc...	Share of men who smoke, most recent year avail...
handwashing_facilities	United Nations Statistics Division	Share of the population with basic handwashing...
hospital_beds_per_thousand	OECD, Eurostat, World Bank, national governmen...	Hospital beds per 1,000 people, most recent ye...
life_expectancy	James C. Riley, Clio Infra, United Nations Pop...	Life expectancy at birth in 2019
human_development_index	United Nations Development Programme (UNDP)	A composite index measuring average achievemen...

	iso_code	continent	location	date	total_cases	new_cases	new_cases_smoothed	total_deaths	new_deaths	new_deaths_smoothed	...	gdp_per_capita	extreme_poverty	cardiovasc_death_rate	diabetes_prevalence	female_smokers	male_smokers	handwashing_facilities	hospital_beds_per_thousand	life_expectancy	human_development_index
0	AFG	Asia	Afghanistan	2020-02-24	1.0	1.0	0.000	0.0	0.0	0.000	...	1803.987	0.0	597.029	9.59	0.0	0.0	37.746	0.5	64.83	0.511
1	AFG	Asia	Afghanistan	2020-02-25	1.0	0.0	0.000	0.0	0.0	0.000	...	1803.987	0.0	597.029	9.59	0.0	0.0	37.746	0.5	64.83	0.511
2	AFG	Asia	Afghanistan	2020-02-26	1.0	0.0	0.000	0.0	0.0	0.000	...	1803.987	0.0	597.029	9.59	0.0	0.0	37.746	0.5	64.83	0.511
3	AFG	Asia	Afghanistan	2020-02-27	1.0	0.0	0.000	0.0	0.0	0.000	...	1803.987	0.0	597.029	9.59	0.0	0.0	37.746	0.5	64.83	0.511
4	AFG	Asia	Afghanistan	2020-02-28	1.0	0.0	0.000	0.0	0.0	0.000	...	1803.987	0.0	597.029	9.59	0.0	0.0	37.746	0.5	64.83	0.511
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
77065	ZWE	Africa	Zimbabwe	2021-03-20	36662.0	10.0	27.286	1510.0	0.0	1.286	...	1899.775	21.4	307.846	1.82	1.6	30.7	36.791	1.7	61.49	0.571
77066	ZWE	Africa	Zimbabwe	2021-03-21	36665.0	3.0	25.857	1512.0	2.0	1.286	...	1899.775	21.4	307.846	1.82	1.6	30.7	36.791	1.7	61.49	0.571
77067	ZWE	Africa	Zimbabwe	2021-03-22	36684.0	19.0	25.714	1514.0	2.0	1.429	...	1899.775	21.4	307.846	1.82	1.6	30.7	36.791	1.7	61.49	0.571
77068	ZWE	Africa	Zimbabwe	2021-03-23	36717.0	33.0	26.000	1516.0	2.0	1.286	...	1899.775	21.4	307.846	1.82	1.6	30.7	36.791	1.7	61.49	0.571
77069	ZWE	Africa	Zimbabwe	2021-03-24	36749.0	32.0	28.143	1516.0	0.0	1.143	...	1899.775	21.4	307.846	1.82	1.6	30.7	36.791	1.7	61.49	0.571

	total_cases	new_cases	new_cases_smoothed	total_deaths	new_deaths	new_deaths_smoothed	total_cases_per_million	new_cases_per_million	new_cases_smoothed_per_million	total_deaths_per_million	new_deaths_per_million	new_deaths_smoothed_per_million	reproduction_rate	icu_patients	icu_patients_per_million	hosp_patients	hosp_patients_per_million	weekly_icu_admissions	weekly_icu_admissions_per_million	weekly_hosp_admissions	weekly_hosp_admissions_per_million	new_tests	total_tests	total_tests_per_thousand	new_tests_per_thousand	new_tests_smoothed	new_tests_smoothed_per_thousand	positive_rate	tests_per_case	total_vaccinations	people_vaccinated	people_fully_vaccinated	new_vaccinations	new_vaccinations_smoothed	total_vaccinations_per_hundred	people_vaccinated_per_hundred	people_fully_vaccinated_per_hundred	new_vaccinations_smoothed_per_million	stringency_index	population	population_density	median_age	aged_65_older	aged_70_older	gdp_per_capita	extreme_poverty	cardiovasc_death_rate	diabetes_prevalence	female_smokers	male_smokers	handwashing_facilities	hospital_beds_per_thousand	life_expectancy	human_development_index
count	77070.000000	77070.000000	77070.000000	77070.000000	77070.000000	77070.000000	77070.000000	77070.000000	77070.000000	77070.000000	77070.000000	77070.000000	77070.000000	77070.000000	77070.000000	77070.000000	77070.000000	77070.000000	77070.000000	77070.000000	77070.000000	77070.000000	77070.000000	77070.000000	77070.000000	77070.000000	77070.000000	77070.000000	77070.000000	77070.000000	77070.000000	77070.000000	77070.000000	77070.000000	77070.000000	77070.000000	77070.000000	77070.000000	77070.000000	77070.000000	77070.000000	77070.000000	77070.000000	77070.000000	77070.000000	77070.000000	77070.000000	77070.000000	77070.000000	77070.000000	77070.000000	77070.000000	77070.000000	77070.000000
mean	677674.915972	5156.367264	5091.575296	17343.162125	114.563436	113.434994	8053.030230	67.126746	66.053063	163.833401	1.218017	1.201153	0.820087	103.015246	2.400628	575.314467	19.399735	2.326418	0.173275	60.116585	1.738200	17672.794979	2208022.734566	81.155104	0.728180	19388.871000	0.789797	0.044106	80.458399	571741.458427	355114.250344	117109.299338	18091.716582	18357.058998	0.587913	0.379025	0.143937	261.998793	50.403207	129582630.083145	315.944330	27.678372	7.872207	5.017944	17407.783511	8.247956	236.048949	7.251116	7.591040	23.182623	23.477190	2.545148	69.511148	0.666942
std	4785606.105903	32284.878882	31732.971959	109921.154810	675.109369	653.120183	15991.109103	169.203743	142.079674	320.885600	3.637859	2.764875	0.506992	1033.079120	10.938436	4708.424611	85.374816	56.777199	3.744918	1546.076673	31.941407	103166.215837	15497037.363906	270.155814	3.167138	101013.696854	2.709296	0.082784	626.781304	8894975.985299	5304336.578280	1998808.553192	285317.081287	242306.558801	4.930788	3.077585	1.701309	1526.630775	28.872054	693951987.829101	1597.074334	12.433716	6.481725	4.369372	19629.624551	16.967133	133.867844	4.299541	10.018281	18.664640	33.322814	2.519112	17.529012	0.247254
min	0.000000	-74347.000000	-6223.000000	0.000000	-1918.000000	-232.143000	0.000000	-2153.437000	-276.825000	0.000000	-76.445000	-10.921000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	-239172.000000	0.000000	0.000000	-23.010000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000
25%	687.250000	1.000000	4.429000	10.000000	0.000000	0.000000	125.542000	0.061000	0.746250	1.681250	0.000000	0.000000	0.530000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	31.480000	2540916.000000	24.282000	19.600000	3.002000	1.756000	2896.913000	0.000000	140.448000	4.610000	0.000000	0.000000	0.000000	0.700000	66.470000	0.555000
50%	7979.000000	56.000000	63.714000	132.000000	1.000000	0.857000	1055.234500	5.931000	7.627000	20.002500	0.020000	0.101000	0.960000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	84.000000	0.006000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	55.560000	10099270.000000	80.080000	29.000000	5.344000	3.212000	10727.146000	0.500000	232.347000	6.930000	2.100000	24.500000	0.000000	2.000000	74.160000	0.737000
75%	88865.000000	667.000000	674.714250	1743.000000	11.000000	11.571000	7379.644000	56.729250	62.636000	143.650500	0.809000	0.987000	1.130000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	3875.750000	385894.750000	31.429500	0.377000	5631.750000	0.533000	0.052000	18.100000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	73.150000	36910558.000000	204.430000	38.000000	13.260000	8.353000	25063.846000	4.500000	318.949000	9.750000	13.000000	37.600000	47.782000	3.600000	78.490000	0.828000
max	124777130.000000	880902.000000	739564.429000	2743519.000000	17903.000000	14431.429000	150624.474000	8652.658000	2648.773000	2416.171000	218.329000	63.140000	6.740000	30028.000000	189.561000	129812.000000	1042.535000	4037.019000	276.325000	116385.000000	2656.911000	2945871.000000	360470276.000000	4076.330000	327.086000	1864511.000000	59.929000	0.742000	44258.700000	489031670.000000	286729839.000000	110978514.000000	20129652.000000	12582892.000000	162.020000	89.730000	72.290000	54264.000000	100.000000	7794798729.000000	20546.766000	48.200000	27.049000	18.493000	116935.600000	77.600000	724.417000	30.530000	44.000000	78.100000	98.999000	13.800000	86.750000	0.957000

	count	mean	std	min	25%	50%	75%	max
total_cases	77070.000000	677674.915972	4785606.105903	0.000000	687.250000	7979.000000	88865.000000	124777130.000000
new_cases	77070.000000	5156.367264	32284.878882	-74347.000000	1.000000	56.000000	667.000000	880902.000000
new_cases_smoothed	77070.000000	5091.575296	31732.971959	-6223.000000	4.429000	63.714000	674.714250	739564.429000
total_deaths	77070.000000	17343.162125	109921.154810	0.000000	10.000000	132.000000	1743.000000	2743519.000000
new_deaths	77070.000000	114.563436	675.109369	-1918.000000	0.000000	1.000000	11.000000	17903.000000
new_deaths_smoothed	77070.000000	113.434994	653.120183	-232.143000	0.000000	0.857000	11.571000	14431.429000
total_cases_per_million	77070.000000	8053.030230	15991.109103	0.000000	125.542000	1055.234500	7379.644000	150624.474000
new_cases_per_million	77070.000000	67.126746	169.203743	-2153.437000	0.061000	5.931000	56.729250	8652.658000
new_cases_smoothed_per_million	77070.000000	66.053063	142.079674	-276.825000	0.746250	7.627000	62.636000	2648.773000
total_deaths_per_million	77070.000000	163.833401	320.885600	0.000000	1.681250	20.002500	143.650500	2416.171000
new_deaths_per_million	77070.000000	1.218017	3.637859	-76.445000	0.000000	0.020000	0.809000	218.329000
new_deaths_smoothed_per_million	77070.000000	1.201153	2.764875	-10.921000	0.000000	0.101000	0.987000	63.140000
reproduction_rate	77070.000000	0.820087	0.506992	0.000000	0.530000	0.960000	1.130000	6.740000
icu_patients	77070.000000	103.015246	1033.079120	0.000000	0.000000	0.000000	0.000000	30028.000000
icu_patients_per_million	77070.000000	2.400628	10.938436	0.000000	0.000000	0.000000	0.000000	189.561000
hosp_patients	77070.000000	575.314467	4708.424611	0.000000	0.000000	0.000000	0.000000	129812.000000
hosp_patients_per_million	77070.000000	19.399735	85.374816	0.000000	0.000000	0.000000	0.000000	1042.535000
weekly_icu_admissions	77070.000000	2.326418	56.777199	0.000000	0.000000	0.000000	0.000000	4037.019000
weekly_icu_admissions_per_million	77070.000000	0.173275	3.744918	0.000000	0.000000	0.000000	0.000000	276.325000
weekly_hosp_admissions	77070.000000	60.116585	1546.076673	0.000000	0.000000	0.000000	0.000000	116385.000000
weekly_hosp_admissions_per_million	77070.000000	1.738200	31.941407	0.000000	0.000000	0.000000	0.000000	2656.911000
new_tests	77070.000000	17672.794979	103166.215837	-239172.000000	0.000000	0.000000	3875.750000	2945871.000000
total_tests	77070.000000	2208022.734566	15497037.363906	0.000000	0.000000	0.000000	385894.750000	360470276.000000
total_tests_per_thousand	77070.000000	81.155104	270.155814	0.000000	0.000000	0.000000	31.429500	4076.330000
new_tests_per_thousand	77070.000000	0.728180	3.167138	-23.010000	0.000000	0.000000	0.377000	327.086000
new_tests_smoothed	77070.000000	19388.871000	101013.696854	0.000000	0.000000	84.000000	5631.750000	1864511.000000
new_tests_smoothed_per_thousand	77070.000000	0.789797	2.709296	0.000000	0.000000	0.006000	0.533000	59.929000
positive_rate	77070.000000	0.044106	0.082784	0.000000	0.000000	0.000000	0.052000	0.742000
tests_per_case	77070.000000	80.458399	626.781304	0.000000	0.000000	0.000000	18.100000	44258.700000
total_vaccinations	77070.000000	571741.458427	8894975.985299	0.000000	0.000000	0.000000	0.000000	489031670.000000
people_vaccinated	77070.000000	355114.250344	5304336.578280	0.000000	0.000000	0.000000	0.000000	286729839.000000
people_fully_vaccinated	77070.000000	117109.299338	1998808.553192	0.000000	0.000000	0.000000	0.000000	110978514.000000
new_vaccinations	77070.000000	18091.716582	285317.081287	0.000000	0.000000	0.000000	0.000000	20129652.000000
new_vaccinations_smoothed	77070.000000	18357.058998	242306.558801	0.000000	0.000000	0.000000	0.000000	12582892.000000
total_vaccinations_per_hundred	77070.000000	0.587913	4.930788	0.000000	0.000000	0.000000	0.000000	162.020000
people_vaccinated_per_hundred	77070.000000	0.379025	3.077585	0.000000	0.000000	0.000000	0.000000	89.730000
people_fully_vaccinated_per_hundred	77070.000000	0.143937	1.701309	0.000000	0.000000	0.000000	0.000000	72.290000
new_vaccinations_smoothed_per_million	77070.000000	261.998793	1526.630775	0.000000	0.000000	0.000000	0.000000	54264.000000
stringency_index	77070.000000	50.403207	28.872054	0.000000	31.480000	55.560000	73.150000	100.000000
population	77070.000000	129582630.083145	693951987.829101	0.000000	2540916.000000	10099270.000000	36910558.000000	7794798729.000000
population_density	77070.000000	315.944330	1597.074334	0.000000	24.282000	80.080000	204.430000	20546.766000
median_age	77070.000000	27.678372	12.433716	0.000000	19.600000	29.000000	38.000000	48.200000
aged_65_older	77070.000000	7.872207	6.481725	0.000000	3.002000	5.344000	13.260000	27.049000
aged_70_older	77070.000000	5.017944	4.369372	0.000000	1.756000	3.212000	8.353000	18.493000
gdp_per_capita	77070.000000	17407.783511	19629.624551	0.000000	2896.913000	10727.146000	25063.846000	116935.600000
extreme_poverty	77070.000000	8.247956	16.967133	0.000000	0.000000	0.500000	4.500000	77.600000
cardiovasc_death_rate	77070.000000	236.048949	133.867844	0.000000	140.448000	232.347000	318.949000	724.417000
diabetes_prevalence	77070.000000	7.251116	4.299541	0.000000	4.610000	6.930000	9.750000	30.530000
female_smokers	77070.000000	7.591040	10.018281	0.000000	0.000000	2.100000	13.000000	44.000000
male_smokers	77070.000000	23.182623	18.664640	0.000000	0.000000	24.500000	37.600000	78.100000
handwashing_facilities	77070.000000	23.477190	33.322814	0.000000	0.000000	0.000000	47.782000	98.999000
hospital_beds_per_thousand	77070.000000	2.545148	2.519112	0.000000	0.700000	2.000000	3.600000	13.800000
life_expectancy	77070.000000	69.511148	17.529012	0.000000	66.470000	74.160000	78.490000	86.750000
human_development_index	77070.000000	0.666942	0.247254	0.000000	0.555000	0.737000	0.828000	0.957000

		total_cases		total_deaths		total_tests		total_vaccinations
		mean	max	mean	max	mean	max	mean	max
continent	location
Asia	Afghanistan	33036.979747	56192.000000	1255.562025	2466.000000	0.000000	0.000000	157.468354	54000.000000
	Armenia	73631.920308	186184.000000	1303.570694	3398.000000	186349.894602	804602.000000	0.000000	0.000000
	Azerbaijan	82843.344473	249492.000000	1084.118252	3404.000000	0.000000	0.000000	9776.629820	482664.000000
	Bahrain	56315.286076	138283.000000	205.959494	507.000000	1131745.949367	3414888.000000	31318.539241	694679.000000
	Bangladesh	293725.217054	580808.000000	4263.493540	8763.000000	1776430.472868	4406190.000000	190865.229974	5069049.000000
	Bhutan	322.265625	870.000000	0.197917	1.000000	162063.768229	578215.000000	0.000000	0.000000
	Brunei	148.136483	206.000000	2.482940	3.000000	0.000000	0.000000	0.000000	0.000000
	Cambodia	290.912530	1872.000000	0.068558	5.000000	0.000000	0.000000	4496.269504	296149.000000
	China	85850.878505	101603.000000	4241.757009	4840.000000	584112.149533	160000000.000000	1201525.700935	82850000.000000
	Georgia	78585.465649	278628.000000	914.715013	3722.000000	0.000000	0.000000	0.000000	0.000000
	Hong Kong	0.000000	0.000000	0.000000	0.000000	511797.471154	9918161.000000	44650.961538	412800.000000
	India	4739064.090476	11787534.000000	71561.492857	160692.000000	73091790.300000	234445774.000000	2400933.764286	53145709.000000
	Indonesia	403395.180412	1476452.000000	12367.747423	39983.000000	1867211.881443	8076608.000000	380110.059278	9330853.000000
	Iran	608130.857500	1823317.000000	27748.397500	62045.000000	2296391.357500	11844528.000000	342.982500	124193.000000
	Iraq	303169.220253	809092.000000	6894.774684	14095.000000	1942520.369620	7654329.000000	0.000000	0.000000
	Israel	245637.155388	830028.000000	1896.431078	6154.000000	4281771.330827	14566108.000000	1240150.102757	9859591.000000
	Japan	118469.039720	460595.000000	2100.789720	8929.000000	2166647.432243	8752281.000000	12341.233645	741180.000000
	Jordan	116229.506460	562857.000000	1429.912145	6181.000000	1264200.731266	5477803.000000	3459.449612	320140.000000
	Kazakhstan	122088.761273	286352.000000	1573.506631	3209.000000	3158949.066313	8340824.000000	621.196286	109995.000000
	Kuwait	90370.637975	223042.000000	551.473418	1256.000000	732095.989873	1967210.000000	1449.367089	360000.000000
	Kyrgyzstan	44161.645161	87758.000000	868.908602	1498.000000	0.000000	0.000000	0.000000	0.000000
	Laos	27.775956	49.000000	0.000000	0.000000	0.000000	0.000000	111.289617	40732.000000
	Lebanon	95626.580402	448721.000000	992.512563	5903.000000	0.000000	0.000000	6053.213568	166015.000000
	Macao	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	15667.688889	40701.000000
	Malaysia	61834.037647	336808.000000	291.442353	1246.000000	1827237.668235	7184509.000000	13987.435294	481989.000000
	Maldives	8496.638743	22929.000000	28.730366	66.000000	173916.455497	602393.000000	9762.178010	212711.000000
	Mongolia	799.589474	5895.000000	0.521053	5.000000	299077.194737	2078713.000000	5305.384211	244550.000000
	Myanmar	50393.495868	142292.000000	1116.595041	3204.000000	588767.490358	2482290.000000	1057.300275	380000.000000
	Nepal	102944.381176	276389.000000	756.908235	3020.000000	823727.943529	2218722.000000	5350.414118	1600000.000000
	Northern Cyprus	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	1774.222222	11000.000000
	Oman	77215.577215	153105.000000	767.263291	1644.000000	0.000000	0.000000	5163.670886	129198.000000
	Pakistan	287125.535533	640988.000000	6065.885787	14028.000000	3149839.809645	9817491.000000	1276.340102	350000.000000
	Palestine	60084.753247	230076.000000	610.467532	2501.000000	0.000000	0.000000	0.000000	0.000000
	Philippines	236426.361905	684311.000000	4721.490476	13039.000000	3070007.752381	9128646.000000	3552.002381	508332.000000
	Qatar	101446.748718	175332.000000	160.161538	278.000000	703702.166667	1666658.000000	10033.471795	658325.000000
	Saudi Arabia	246783.657216	386300.000000	3615.997423	6624.000000	6004594.435567	14664169.000000	140753.902062	3646851.000000
	Singapore	40857.341920	60236.000000	21.578454	30.000000	370263.943794	8055714.000000	15000.899297	1109000.000000
	South Korea	30042.668998	100276.000000	525.081585	1709.000000	2010792.480186	7252832.000000	27435.603730	735815.000000
	Sri Lanka	18852.978723	91018.000000	96.737589	552.000000	553391.711584	2342977.000000	53878.217494	838355.000000
	Syria	5578.801630	17896.000000	333.440217	1195.000000	0.000000	0.000000	0.000000	0.000000
	Taiwan	510.352535	1009.000000	6.087558	10.000000	85540.248848	184201.000000	11.050691	3218.000000
	Tajikistan	9452.626140	13308.000000	71.544073	90.000000	0.000000	0.000000	0.000000	0.000000
	Thailand	6010.717489	28443.000000	49.529148	92.000000	903484.558296	2991347.000000	441.914798	102050.000000
	Timor	43.769022	372.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000
	Turkey	859194.799472	3091282.000000	11278.145119	30462.000000	12433450.179420	36355374.000000	1114724.168865	13969867.000000
	United Arab Emirates	118747.838480	446594.000000	437.964371	1456.000000	10376247.289786	35576712.000000	832309.724466	7603328.000000
	Uzbekistan	43351.965333	81678.000000	338.970667	623.000000	0.000000	0.000000	0.000000	0.000000
	Vietnam	913.517564	2576.000000	18.297424	35.000000	91288.873536	1469955.000000	771.723653	39817.000000
	Yemen	1652.025788	3703.000000	463.796562	800.000000	0.000000	0.000000	0.000000	0.000000

	date	total_cases	new_cases	total_deaths	new_deaths	aged_65_older	aged_70_older	gdp_per_capita	diabetes_prevalence	female_smokers	male_smokers	hospital_beds_per_thousand
0	2020-01-22	557	0	17	0	8.696	5.355	15469.2	8.51	6.434	34.635	2.705
1	2020-01-23	655	98	18	1	8.696	5.355	15469.2	8.51	6.434	34.635	2.705
2	2020-01-24	941	286	26	8	8.696	5.355	15469.2	8.51	6.434	34.635	2.705
3	2020-01-25	1433	492	42	16	8.696	5.355	15469.2	8.51	6.434	34.635	2.705
4	2020-01-26	2118	685	56	14	8.696	5.355	15469.2	8.51	6.434	34.635	2.705

	total_cases	new_cases	total_deaths	new_deaths	aged_65_older	aged_70_older	gdp_per_capita	diabetes_prevalence	female_smokers	male_smokers	hospital_beds_per_thousand	temp
date
2021-03-20	1.22815e+08	498423	2.70964e+06	8194	8.696	5.355	15469.2	8.51	6.434	34.635	2.705	NaN
2021-03-21	1.23209e+08	393986	2.7153e+06	5655	8.696	5.355	15469.2	8.51	6.434	34.635	2.705	NaN
2021-03-22	1.23691e+08	481960	2.72295e+06	7656	8.696	5.355	15469.2	8.51	6.434	34.635	2.705	NaN
2021-03-23	1.24205e+08	514125	2.73408e+06	11131	8.696	5.355	15469.2	8.51	6.434	34.635	2.705	NaN
2021-03-24	1.24777e+08	572494	2.74352e+06	9437	8.696	5.355	15469.2	8.51	6.434	34.635	2.705	NaN

	total_cases	new_cases	total_deaths	new_deaths	aged_65_older	aged_70_older	gdp_per_capita	diabetes_prevalence	female_smokers	male_smokers	hospital_beds_per_thousand	temp	forecast
2021-03-25	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2021-03-26	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2021-03-27	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2021-03-28	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2021-03-29	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2021-03-30	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2021-03-31	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2021-04-01	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2021-04-02	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2021-04-03	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2021-04-04	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2021-04-05	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2021-04-06	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2021-04-07	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2021-04-08	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2021-04-09	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2021-04-10	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2021-04-11	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2021-04-12	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2021-04-13	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2021-04-14	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2021-04-15	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2021-04-16	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2021-04-17	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2021-04-18	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2021-04-19	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2021-04-20	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2021-04-21	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2021-04-22	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2021-04-23	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN

	total_cases	new_cases	total_deaths	new_deaths	aged_65_older	aged_70_older	gdp_per_capita	diabetes_prevalence	female_smokers	male_smokers	hospital_beds_per_thousand	temp	forecast
2021-03-25	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	2.77893e+06
2021-03-26	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	2.81166e+06
2021-03-27	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	2.81226e+06
2021-03-28	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	2.8226e+06
2021-03-29	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	2.80351e+06
2021-03-30	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	2.76946e+06
2021-03-31	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	2.78761e+06
2021-04-01	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	2.81667e+06
2021-04-02	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	2.869e+06
2021-04-03	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	2.8754e+06
2021-04-04	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	2.88504e+06
2021-04-05	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	2.87069e+06
2021-04-06	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	2.85007e+06
2021-04-07	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	2.84556e+06
2021-04-08	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	2.90634e+06
2021-04-09	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	2.9296e+06
2021-04-10	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	2.94284e+06
2021-04-11	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	2.95548e+06
2021-04-12	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	2.94953e+06
2021-04-13	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	2.91055e+06
2021-04-14	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	2.92142e+06
2021-04-15	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	2.98401e+06
2021-04-16	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	3.01448e+06
2021-04-17	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	3.03195e+06
2021-04-18	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	3.03196e+06
2021-04-19	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	3.02225e+06
2021-04-20	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	2.98422e+06
2021-04-21	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	3.0285e+06
2021-04-22	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	3.06801e+06
2021-04-23	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	3.08549e+06

	death_rate	total_deaths_per_million	aged_65_older	extreme_poverty	icu_patients	life_expectancy	cardiovasc_death_rate	diabetes_prevalence	human_development_index	population_density	aged_70_older	population_coverage
death_rate	1.000000	0.011013	0.019572	-0.004681	0.002747	0.000893	0.007706	-0.016305	-0.006115	0.000207	0.022099	-0.027709
total_deaths_per_million	0.011013	1.000000	0.264212	-0.190900	0.204100	0.087164	-0.208577	-0.043818	0.133330	-0.024345	0.266664	0.281192
aged_65_older	0.019572	0.264212	1.000000	-0.313919	0.151497	0.494730	-0.060358	0.078084	0.689752	-0.037197	0.965827	0.233370
extreme_poverty	-0.004681	-0.190900	-0.313919	1.000000	-0.042707	-0.145721	0.191647	-0.272834	-0.251718	-0.056249	-0.315198	-0.128822
icu_patients	0.002747	0.204100	0.151497	-0.042707	1.000000	0.061696	-0.068135	0.025675	0.101118	-0.012709	0.153405	0.121640
life_expectancy	0.000893	0.087164	0.494730	-0.145721	0.061696	1.000000	0.169771	0.435127	0.747783	0.124059	0.485039	0.166888
cardiovasc_death_rate	0.007706	-0.208577	-0.060358	0.191647	-0.068135	0.169771	1.000000	0.246384	0.155555	-0.180265	-0.097281	-0.097969
diabetes_prevalence	-0.016305	-0.043818	0.078084	-0.272834	0.025675	0.435127	0.246384	1.000000	0.462258	0.022870	0.019279	0.075299
human_development_index	-0.006115	0.133330	0.689752	-0.251718	0.101118	0.747783	0.155555	0.462258	1.000000	-0.131790	0.638403	0.248644
population_density	0.000207	-0.024345	-0.037197	-0.056249	-0.012709	0.124059	-0.180265	0.022870	-0.131790	1.000000	-0.046807	0.001421
aged_70_older	0.022099	0.266664	0.965827	-0.315198	0.153405	0.485039	-0.097281	0.019279	0.638403	-0.046807	1.000000	0.225436
population_coverage	-0.027709	0.281192	0.233370	-0.128822	0.121640	0.166888	-0.097969	0.075299	0.248644	0.001421	0.225436	1.000000

		total_cases		total_deaths		total_tests		total_vaccinations
		mean	max	mean	max	mean	max	mean	max
continent	location
Europe	Albania	28453.350254	122295.000000	558.969543	2171.000000	121265.670051	500736.000000	745.545685	53992.000000
	Andorra	3930.193299	11638.000000	61.801546	114.000000	4868.025773	162071.000000	97.314433	9288.000000
	Austria	147729.319797	523269.000000	2579.515228	9151.000000	3264387.454315	20316556.000000	101121.931472	1354694.000000
	Belarus	107625.797954	313852.000000	826.744246	2184.000000	520832.547315	5178695.000000	130.291560	30000.000000
	Belgium	276835.050602	849090.000000	11344.139759	22786.000000	3375895.848193	10322890.000000	117202.016867	1504722.000000
	Bosnia and Herzegovina	48446.706494	158198.000000	1707.005195	6067.000000	212899.885714	736787.000000	0.000000	0.000000
	Bulgaria	80717.057592	317116.000000	3010.376963	12413.000000	528628.609948	1950384.000000	29123.960733	401309.000000
	Croatia	74909.441624	260636.000000	1479.116751	5828.000000	388709.421320	1477537.000000	9150.781726	390657.000000
	Cyprus	9787.737533	43286.000000	65.144357	248.000000	620716.456693	3203608.000000	1488.000000	129438.000000
	Czechia	335113.417303	1486510.000000	5342.554707	25258.000000	0.000000	0.000000	109238.229008	1459631.000000
	Denmark	64371.411330	228586.000000	867.157635	2406.000000	5007588.948276	20071320.000000	87708.938424	978561.000000
	Estonia	15151.530457	99008.000000	156.946701	823.000000	328193.824873	1090150.000000	14882.893401	229921.000000
	Faeroe Islands	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	2286.264151	9427.000000
	Finland	17757.149644	73516.000000	348.729216	809.000000	1131973.406176	3764309.000000	55646.038005	847501.000000
	France	1168375.671362	4374774.000000	37394.016432	93083.000000	0.000000	0.000000	557596.647887	9122922.000000
	Germany	726387.635934	2722988.000000	18785.702128	75484.000000	2345986.503546	47511887.000000	869029.943262	11447546.000000
	Gibraltar	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	26476.567568	54587.000000
	Greece	57024.173804	245405.000000	1806.478589	7649.000000	1594765.599496	6101959.000000	107891.556675	1536957.000000
	Guernsey	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	2345.041667	29383.000000
	Hungary	128101.093264	593710.000000	4112.603627	18952.000000	1078613.525907	3864469.000000	148775.590674	2272123.000000
	Iceland	3323.905852	6144.000000	15.452926	29.000000	133256.577608	292069.000000	2527.862595	58029.000000
	Ireland	67763.733503	232164.000000	1931.251269	4628.000000	1292716.428934	3816117.000000	50409.139594	680015.000000
	Isle of Man	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	15432.666667	33336.000000
	Italy	900053.073986	3440862.000000	43391.620525	106339.000000	13325498.613365	46890903.000000	659466.143198	8506277.000000
	Jersey	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	5889.698113	48732.000000
	Kosovo	24605.470745	84172.000000	654.723404	1811.000000	0.000000	0.000000	0.000000	0.000000
	Latvia	19239.670051	98870.000000	340.048223	1851.000000	466180.147208	1710928.000000	8476.692893	116477.000000
	Liechtenstein	808.072539	2636.000000	14.248705	56.000000	0.000000	0.000000	77.046632	4345.000000
	Lithuania	51864.849105	211011.000000	767.245524	3510.000000	832604.626598	2264247.000000	35681.023018	437588.000000
	Luxembourg	19744.544304	59907.000000	237.637975	728.000000	813251.303797	2292625.000000	3908.503797	77997.000000
	Malta	6240.736077	28510.000000	86.150121	377.000000	259408.774818	783735.000000	10839.341404	155678.000000
	Moldova	69826.371728	219988.000000	1574.246073	4661.000000	0.000000	0.000000	436.172775	23454.000000
	Monaco	525.135897	2210.000000	5.792308	28.000000	0.000000	0.000000	92.546154	18081.000000
	Montenegro	23192.356568	88550.000000	322.970509	1224.000000	0.000000	0.000000	190.898123	10809.000000
	Netherlands	346866.354430	1238664.000000	7664.577215	16510.000000	361934.688608	7184008.000000	25006.918987	2097980.000000
	North Macedonia	35540.699746	122227.000000	1122.035623	3545.000000	201511.223919	589665.000000	13.486005	5300.000000
	Norway	25270.388889	90104.000000	303.800505	656.000000	1402064.702020	4383065.000000	66334.941919	783851.000000
	Poland	528251.608808	2120671.000000	12198.134715	50340.000000	3736627.455959	10874141.000000	390979.800518	5193835.000000

		total_cases		total_deaths		total_tests		total_vaccinations
		mean	max	mean	max	mean	max	mean	max
continent	location
North America	Anguilla	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	417.727273	5348.000000
	Antigua and Barbuda	169.283820	1080.000000	5.018568	28.000000	0.000000	0.000000	132.204244	25677.000000
	Bahamas	3918.558824	8935.000000	86.695187	188.000000	0.000000	0.000000	0.294118	110.000000
	Barbados	595.096515	3582.000000	9.868633	40.000000	0.000000	0.000000	3995.943700	62765.000000
	Belize	4270.242507	12410.000000	99.130790	317.000000	0.000000	0.000000	358.465940	18182.000000
	Bermuda	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	3017.500000	34204.000000
	Canada	271425.382075	951438.000000	9683.693396	22739.000000	2838719.018868	26592828.000000	298111.115566	4393876.000000
	Cayman Islands	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	5034.898876	43023.000000
	Costa Rica	80207.346354	213438.000000	1027.205729	2908.000000	212411.963542	635447.000000	4172.424479	312425.000000
	Cuba	11337.888889	68986.000000	127.645503	405.000000	788100.238095	2788164.000000	0.000000	0.000000
	Dominica	53.769022	160.000000	0.000000	0.000000	0.000000	0.000000	56.432065	13565.000000
	Dominican Republic	101316.000000	250579.000000	1583.737789	3289.000000	426589.174807	1275756.000000	12372.028278	800000.000000
	El Salvador	27129.948787	63766.000000	793.153639	1990.000000	348545.932615	802126.000000	467.687332	49000.000000
	Greenland	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	226.882353	5130.000000
	Grenada	55.168478	154.000000	0.220109	1.000000	0.000000	0.000000	31.934783	8606.000000
	Guatemala	75033.069652	190208.000000	2678.358209	6749.000000	311200.547264	1007600.000000	1689.584577	78350.000000
	Haiti	7207.764865	12732.000000	164.937838	251.000000	0.000000	0.000000	0.000000	0.000000
	Honduras	72053.308707	184821.000000	1924.569921	4506.000000	0.000000	0.000000	313.308707	43073.000000
	Jamaica	7508.461741	36670.000000	147.472296	545.000000	49053.058047	261957.000000	74.393140	16096.000000
	Mexico	683881.287305	2208755.000000	64349.064588	199627.000000	1604828.498886	5457521.000000	314214.454343	6119298.000000
	Montserrat	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	51.096774	932.000000
	Nicaragua	3972.064690	6629.000000	114.377358	177.000000	0.000000	0.000000	0.000000	0.000000
	Panama	129720.325459	352082.000000	2356.238845	6065.000000	637085.776903	2063565.000000	16947.724409	320079.000000
	Saint Kitts and Nevis	22.356164	44.000000	0.000000	0.000000	0.000000	0.000000	39.679452	7580.000000
	Saint Lucia	539.965426	4161.000000	6.015957	58.000000	0.000000	0.000000	105.664894	20247.000000
	Saint Vincent and the Grenadines	284.574468	1703.000000	1.007979	10.000000	0.000000	0.000000	48.763298	9383.000000
	Trinidad and Tobago	3523.718085	7903.000000	64.718085	141.000000	31237.111702	108872.000000	3.805851	991.000000
	Turks and Caicos Islands	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	276.812500	11283.000000
	United States	9200016.745327	30011839.000000	200326.845794	545281.000000	115418878.724299	360470276.000000	9996851.226636	130473853.000000

	total_cases	new_cases	new_cases_smoothed	total_deaths	new_deaths	new_deaths_smoothed	total_cases_per_million	new_cases_per_million	new_cases_smoothed_per_million	total_deaths_per_million	new_deaths_per_million	new_deaths_smoothed_per_million	reproduction_rate	icu_patients	icu_patients_per_million	hosp_patients	hosp_patients_per_million	weekly_icu_admissions	weekly_icu_admissions_per_million	weekly_hosp_admissions	weekly_hosp_admissions_per_million	new_tests	total_tests	total_tests_per_thousand	new_tests_per_thousand	new_tests_smoothed	new_tests_smoothed_per_thousand	positive_rate	tests_per_case	total_vaccinations	people_vaccinated	people_fully_vaccinated	new_vaccinations	new_vaccinations_smoothed	total_vaccinations_per_hundred	people_vaccinated_per_hundred	people_fully_vaccinated_per_hundred	new_vaccinations_smoothed_per_million	stringency_index	population	population_density	median_age	aged_65_older	aged_70_older	gdp_per_capita	extreme_poverty	cardiovasc_death_rate	diabetes_prevalence	female_smokers	male_smokers	handwashing_facilities	hospital_beds_per_thousand	life_expectancy	human_development_index	death_rate	population_coverage
total_cases	1.000000	0.873299	0.887326	0.983802	0.844898	0.874311	0.139983	0.066990	0.081245	0.170065	0.070894	0.094530	-0.053071	0.162801	0.042694	0.151277	0.018804	0.003043	-0.001481	0.058707	0.007129	0.174307	0.208973	0.008303	-0.003219	0.182271	-0.004413	-0.031846	-0.016733	0.712460	0.721331	0.647483	0.692255	0.761850	0.064043	0.072061	0.046951	0.050862	-0.145777	0.604423	-0.022153	-0.076723	-0.028295	-0.028550	-0.023804	-0.030642	-0.103841	-0.060529	-0.015806	-0.027955	0.003206	-0.042113	-0.181692	-0.100707	-0.006092	0.008072
new_cases	0.873299	1.000000	0.988773	0.893576	0.927181	0.923855	0.112752	0.111940	0.119187	0.146038	0.095203	0.113769	-0.051866	0.206069	0.064021	0.197164	0.036195	0.003182	-0.002165	0.063908	0.008577	0.195796	0.170978	0.000345	-0.001836	0.198494	-0.003543	-0.022056	-0.019589	0.397744	0.406687	0.342398	0.423192	0.456582	0.026179	0.031040	0.016871	0.019985	-0.161542	0.663643	-0.025421	-0.086865	-0.028929	-0.029054	-0.025630	-0.036858	-0.120033	-0.072324	-0.014293	-0.031863	-0.000690	-0.045091	-0.208493	-0.115151	-0.007238	0.000082
new_cases_smoothed	0.887326	0.988773	1.000000	0.905686	0.919042	0.939814	0.116271	0.101600	0.121108	0.149280	0.091652	0.117967	-0.054293	0.210299	0.064693	0.200710	0.036279	0.007041	0.000604	0.077607	0.013118	0.195842	0.175892	0.001228	-0.002162	0.202367	-0.003136	-0.022012	-0.019675	0.401333	0.410950	0.343239	0.425565	0.465270	0.027150	0.032227	0.017394	0.021369	-0.161955	0.666750	-0.025540	-0.087173	-0.028983	-0.029104	-0.025575	-0.037008	-0.120587	-0.072564	-0.014325	-0.031967	-0.000656	-0.045323	-0.209317	-0.115545	-0.007037	0.000964
total_deaths	0.983802	0.893576	0.905686	1.000000	0.878122	0.908172	0.132280	0.064170	0.077391	0.187699	0.076753	0.102483	-0.058974	0.138530	0.035681	0.131367	0.016267	0.002557	-0.003219	0.049410	0.005419	0.144495	0.162302	-0.002530	-0.008445	0.150797	-0.010849	-0.027306	-0.018711	0.669213	0.682720	0.612810	0.647635	0.712731	0.055957	0.064971	0.039945	0.042584	-0.162855	0.640210	-0.025668	-0.086723	-0.030301	-0.029570	-0.028804	-0.037278	-0.123186	-0.072205	-0.017312	-0.035330	0.004501	-0.049168	-0.205345	-0.114115	-0.001580	-0.002791
new_deaths	0.844898	0.927181	0.919042	0.878122	1.000000	0.971446	0.105325	0.085543	0.096066	0.152548	0.139895	0.146807	-0.058595	0.152748	0.054006	0.149241	0.032983	0.000578	-0.003267	0.028848	0.002964	0.142299	0.127090	-0.009906	-0.009162	0.139789	-0.013333	-0.012012	-0.020913	0.409118	0.424122	0.352113	0.443051	0.475503	0.027266	0.033968	0.017103	0.020999	-0.168757	0.680219	-0.027794	-0.093526	-0.031902	-0.031064	-0.031863	-0.040936	-0.130811	-0.078961	-0.016683	-0.035798	0.003843	-0.048793	-0.222984	-0.123825	0.008751	-0.010189
new_deaths_smoothed	0.874311	0.923855	0.939814	0.908172	0.971446	1.000000	0.110232	0.079037	0.096699	0.159338	0.115099	0.151421	-0.062441	0.155334	0.053846	0.151434	0.032596	0.006131	-0.001292	0.055896	0.009813	0.138761	0.132973	-0.009312	-0.010491	0.144490	-0.013440	-0.012956	-0.021368	0.430561	0.446276	0.371470	0.455294	0.499895	0.029790	0.036938	0.018876	0.023285	-0.172637	0.696445	-0.028440	-0.095688	-0.032605	-0.031741	-0.032466	-0.041875	-0.133946	-0.080754	-0.017074	-0.036638	0.004010	-0.050012	-0.228140	-0.126646	0.009054	-0.009601
total_cases_per_million	0.139983	0.112752	0.116271	0.132280	0.105325	0.110232	1.000000	0.589177	0.707897	0.832519	0.438312	0.579444	0.120428	0.183546	0.367294	0.215116	0.367265	0.079461	0.109429	0.072138	0.091246	0.183280	0.193491	0.450411	0.302120	0.199264	0.381596	0.195474	-0.042327	0.102226	0.122091	0.121083	0.090132	0.103926	0.259621	0.270905	0.205248	0.252964	0.053885	-0.032970	0.026211	0.131134	0.194424	0.185750	0.263228	-0.195027	-0.161619	0.041928	0.293719	0.092356	-0.120164	0.139822	0.125850	0.164803	-0.027033	0.450005
new_cases_per_million	0.066990	0.111940	0.101600	0.064170	0.085543	0.079037	0.589177	1.000000	0.845296	0.481867	0.529812	0.575437	0.164073	0.160596	0.375124	0.202312	0.417123	0.049505	0.073806	0.052648	0.076155	0.136383	0.104212	0.277244	0.246257	0.143992	0.290851	0.273656	-0.044030	0.022416	0.029683	0.026210	0.024383	0.027034	0.128705	0.137584	0.092042	0.144340	0.065433	-0.030167	0.026255	0.132326	0.203414	0.192840	0.187296	-0.157330	-0.109848	0.022538	0.280026	0.089914	-0.110768	0.147645	0.104713	0.142518	-0.031296	0.276778
new_cases_smoothed_per_million	0.081245	0.119187	0.121108	0.077391	0.096066	0.096699	0.707897	0.845296	1.000000	0.576541	0.551165	0.698226	0.175535	0.189905	0.447282	0.237770	0.496662	0.099210	0.142521	0.082740	0.132271	0.158481	0.126210	0.331763	0.278615	0.172172	0.344333	0.322341	-0.051597	0.027523	0.036373	0.031766	0.029043	0.033740	0.154717	0.163011	0.112839	0.173611	0.081502	-0.035172	0.030902	0.155026	0.238161	0.225993	0.219957	-0.184239	-0.129274	0.026538	0.327634	0.105429	-0.129759	0.172387	0.123043	0.167789	-0.036118	0.331275
total_deaths_per_million	0.170065	0.146038	0.149280	0.187699	0.152548	0.159338	0.832519	0.481867	0.576541	1.000000	0.472693	0.628972	0.119414	0.204100	0.383112	0.261345	0.395583	0.071295	0.079008	0.079264	0.087239	0.205217	0.195188	0.281764	0.212308	0.224909	0.263607	0.241955	-0.049870	0.109466	0.133928	0.125900	0.098081	0.111981	0.172962	0.203572	0.129116	0.167460	0.072068	-0.017455	-0.024345	0.139647	0.264212	0.266664	0.199840	-0.190900	-0.208577	-0.043818	0.322129	0.032448	-0.102101	0.145877	0.087164	0.133330	0.011013	0.281192
new_deaths_per_million	0.070894	0.095203	0.091652	0.076753	0.139895	0.115099	0.438312	0.529812	0.551165	0.472693	1.000000	0.762709	0.095960	0.145911	0.380476	0.199831	0.450994	0.042396	0.068112	0.033752	0.074993	0.112728	0.085166	0.167056	0.169868	0.115601	0.195747	0.277142	-0.038076	0.027435	0.036775	0.030197	0.031103	0.033353	0.060029	0.074032	0.042252	0.071417	0.086211	-0.017140	-0.004705	0.126266	0.205329	0.204061	0.111444	-0.125934	-0.093266	-0.016848	0.241715	0.053006	-0.071397	0.135669	0.060736	0.107452	0.041499	0.166596
new_deaths_smoothed_per_million	0.094530	0.113769	0.117967	0.102483	0.146807	0.151421	0.579444	0.575437	0.698226	0.628972	0.762709	1.000000	0.113359	0.186694	0.488927	0.255577	0.579723	0.087281	0.115229	0.077123	0.127038	0.139086	0.114610	0.222477	0.213998	0.152241	0.255733	0.351179	-0.049105	0.038331	0.051013	0.042211	0.040850	0.046262	0.081652	0.099024	0.058145	0.095334	0.115864	-0.022001	-0.006850	0.163924	0.266501	0.265023	0.144866	-0.163241	-0.122150	-0.022155	0.313131	0.068444	-0.092649	0.174781	0.078877	0.140537	0.050350	0.221930
reproduction_rate	-0.053071	-0.051866	-0.054293	-0.058974	-0.058595	-0.062441	0.120428	0.164073	0.175535	0.119414	0.095960	0.113359	1.000000	0.038359	0.090442	0.048543	0.097159	0.025092	0.022445	0.017734	0.026610	0.073901	0.051459	0.125480	0.110145	0.080615	0.131601	0.278298	-0.003857	-0.030006	-0.029790	-0.026950	-0.029028	-0.031482	-0.022365	-0.024410	-0.025124	-0.055871	0.418285	-0.042620	-0.025336	0.380303	0.297362	0.284325	0.180314	-0.013056	0.130563	0.055655	0.240007	0.218915	0.073759	0.175454	0.335661	0.362362	-0.039680	0.123734
icu_patients	0.162801	0.206069	0.210299	0.138530	0.152748	0.155334	0.183546	0.160596	0.189905	0.204100	0.145911	0.186694	0.038359	1.000000	0.458753	0.935074	0.275069	0.057626	0.024773	0.344653	0.083090	0.690000	0.669469	0.121772	0.080062	0.719801	0.101520	0.047549	-0.010720	0.061237	0.077725	0.067141	0.066358	0.085930	0.043712	0.055147	0.029202	0.047276	0.072354	0.008319	-0.012709	0.107756	0.151497	0.153405	0.145825	-0.042707	-0.068135	0.025675	0.143334	0.025450	-0.070255	0.053591	0.061696	0.101118	0.002747	0.121640
icu_patients_per_million	0.042694	0.064021	0.064693	0.035681	0.054006	0.053846	0.367294	0.375124	0.447282	0.383112	0.380476	0.488927	0.090442	0.458753	1.000000	0.483045	0.707340	0.174067	0.195166	0.164179	0.207923	0.261009	0.218538	0.248754	0.220625	0.288673	0.268476	0.145015	-0.021908	0.015185	0.022478	0.017603	0.016815	0.021940	0.087949	0.101489	0.077630	0.078294	0.146991	-0.027411	-0.020730	0.261033	0.361726	0.370842	0.261317	-0.096498	-0.115565	-0.037250	0.345028	0.091639	-0.154625	0.191095	0.142851	0.212406	0.016629	0.248486
hosp_patients	0.151277	0.197164	0.200710	0.131367	0.149241	0.151434	0.215116	0.202312	0.237770	0.261345	0.199831	0.255577	0.048543	0.935074	0.483045	1.000000	0.441399	0.079111	0.033166	0.329184	0.085931	0.669200	0.628154	0.142044	0.110646	0.687931	0.132008	0.084353	-0.012614	0.055850	0.072310	0.058997	0.061275	0.080168	0.050661	0.065647	0.031177	0.055944	0.088651	0.002755	-0.014832	0.136776	0.193626	0.194272	0.153896	-0.053467	-0.082600	0.000378	0.179632	0.036888	-0.086087	0.067655	0.077537	0.119608	0.008422	0.141883
hosp_patients_per_million	0.018804	0.036195	0.036279	0.016267	0.032983	0.032596	0.367265	0.417123	0.496662	0.395583	0.450994	0.579723	0.097159	0.275069	0.707340	0.441399	1.000000	0.131901	0.166846	0.096649	0.152258	0.195968	0.139477	0.279271	0.303007	0.204337	0.348742	0.212793	-0.022366	0.005429	0.010722	0.006278	0.006866	0.009642	0.075386	0.091120	0.060146	0.075445	0.130899	-0.032721	-0.025513	0.272502	0.375090	0.380119	0.216794	-0.102916	-0.066947	-0.064712	0.372980	0.120673	-0.160094	0.221372	0.136558	0.207489	0.014860	0.279005
weekly_icu_admissions	0.003043	0.003182	0.007041	0.002557	0.000578	0.006131	0.079461	0.049505	0.099210	0.071295	0.042396	0.087281	0.025092	0.057626	0.174067	0.079111	0.131901	1.000000	0.725515	0.220394	0.452151	0.001661	-0.002847	0.008412	0.009760	0.034080	0.044116	0.024350	-0.004540	0.000614	0.001050	0.001984	-0.001056	0.000735	0.031182	0.033651	0.031095	0.025843	0.028695	-0.005558	-0.003818	0.046164	0.067115	0.066726	0.039257	-0.019230	-0.031116	-0.012819	0.080165	0.025934	-0.028868	0.039371	0.028865	0.039724	0.005735	0.008347
weekly_icu_admissions_per_million	-0.001481	-0.002165	0.000604	-0.003219	-0.003267	-0.001292	0.109429	0.073806	0.142521	0.079008	0.068112	0.115229	0.022445	0.024773	0.195166	0.033166	0.166846	0.725515	1.000000	0.140524	0.585212	0.001002	-0.001116	0.044417	0.030110	0.013915	0.069451	0.037480	-0.004872	0.000057	0.000306	0.001749	-0.000885	-0.000365	0.052089	0.055773	0.052405	0.043496	0.029328	-0.007745	-0.003449	0.049139	0.070183	0.069022	0.039638	-0.021640	-0.018559	-0.011871	0.078617	0.032343	-0.032599	0.042626	0.029270	0.044653	-0.000961	0.044352
weekly_hosp_admissions	0.058707	0.063908	0.077607	0.049410	0.028848	0.055896	0.072138	0.052648	0.082740	0.079264	0.033752	0.077123	0.017734	0.344653	0.164179	0.329184	0.096649	0.220394	0.140524	1.000000	0.470887	0.163140	0.245938	0.047430	0.017918	0.259606	0.040012	0.028911	-0.004177	0.021460	0.026770	0.025660	0.023381	0.031477	0.016201	0.020380	0.011313	0.018172	0.026908	0.002161	-0.004962	0.042271	0.058547	0.058744	0.050655	-0.015692	-0.020288	0.009368	0.057005	0.012365	-0.027395	0.021849	0.023172	0.037951	0.001121	0.047378
weekly_hosp_admissions_per_million	0.007129	0.008577	0.013118	0.005419	0.002964	0.009813	0.091246	0.076155	0.132271	0.087239	0.074993	0.127038	0.026610	0.083090	0.207923	0.085931	0.152258	0.452151	0.585212	0.470887	1.000000	0.030588	0.042125	0.044750	0.026317	0.056215	0.058943	0.058813	-0.005718	0.002126	0.003464	0.002867	0.001525	0.003501	0.018194	0.021654	0.015675	0.016957	0.029986	-0.007450	-0.005183	0.065229	0.089210	0.089795	0.043188	-0.021650	-0.007272	-0.004986	0.093381	0.034319	-0.038340	0.056964	0.031239	0.048836	0.000323	0.044672
new_tests	0.174307	0.195796	0.195842	0.144495	0.142299	0.138761	0.183280	0.136383	0.158481	0.205217	0.112728	0.139086	0.073901	0.690000	0.261009	0.669200	0.195968	0.001661	0.001002	0.163140	0.030588	1.000000	0.849942	0.233731	0.259457	0.959124	0.225430	0.051202	-0.006162	0.078534	0.100568	0.083422	0.077393	0.092829	0.095845	0.103249	0.047257	0.072714	0.097414	0.055545	-0.015566	0.121203	0.137274	0.132134	0.143559	-0.035966	-0.033107	0.058295	0.130238	0.059621	-0.042951	0.046734	0.072124	0.118912	-0.009695	0.233525
total_tests	0.208973	0.170978	0.175892	0.162302	0.127090	0.132973	0.193491	0.104212	0.126210	0.195188	0.085166	0.114610	0.051459	0.669469	0.218538	0.628154	0.139477	-0.002847	-0.001116	0.245938	0.042125	0.849942	1.000000	0.233809	0.129188	0.875766	0.149112	0.037691	-0.000833	0.137186	0.168038	0.162634	0.133376	0.157880	0.117492	0.121656	0.073759	0.094580	0.071742	0.051921	-0.012175	0.095479	0.101924	0.097349	0.116671	-0.026798	-0.016894	0.059363	0.094132	0.049590	-0.030913	0.031954	0.055938	0.095180	-0.008868	0.233645
total_tests_per_thousand	0.008303	0.000345	0.001228	-0.002530	-0.009906	-0.009312	0.450411	0.277244	0.331763	0.281764	0.167056	0.222477	0.125480	0.121772	0.248754	0.142044	0.279271	0.008412	0.044417	0.047430	0.044750	0.233731	0.233809	1.000000	0.706229	0.235659	0.812857	0.044927	0.049600	0.023658	0.026456	0.024571	0.016388	0.020483	0.292694	0.224494	0.169468	0.232605	0.087400	-0.044317	0.001747	0.241472	0.234369	0.226457	0.380607	-0.127905	-0.094195	0.077472	0.243115	0.133760	-0.125663	0.120964	0.166021	0.248015	-0.027709	1.000000
new_tests_per_thousand	-0.003219	-0.001836	-0.002162	-0.008445	-0.009162	-0.010491	0.302120	0.246257	0.278615	0.212308	0.169868	0.213998	0.110145	0.080062	0.220625	0.110646	0.303007	0.009760	0.030110	0.017918	0.026317	0.259457	0.129188	0.706229	1.000000	0.196450	0.845156	0.033105	0.022278	0.006281	0.008184	0.003731	0.003077	0.003613	0.169418	0.134741	0.092311	0.140532	0.085473	-0.034892	-0.009577	0.195088	0.202458	0.196433	0.267813	-0.099472	-0.069529	0.042594	0.213750	0.110859	-0.102375	0.114020	0.127418	0.190946	-0.019140	0.706128
new_tests_smoothed	0.182271	0.198494	0.202367	0.150797	0.139789	0.144490	0.199264	0.143992	0.172172	0.224909	0.115601	0.152241	0.080615	0.719801	0.288673	0.687931	0.204337	0.034080	0.013915	0.259606	0.056215	0.959124	0.875766	0.235659	0.196450	1.000000	0.237520	0.053082	-0.000262	0.082838	0.106041	0.089119	0.082379	0.099878	0.098991	0.106911	0.050371	0.076593	0.105517	0.055763	-0.011297	0.143814	0.163941	0.161620	0.163135	-0.043558	-0.039967	0.060853	0.155121	0.069802	-0.053294	0.066212	0.083599	0.136239	-0.010426	0.235424
new_tests_smoothed_per_thousand	-0.004413	-0.003543	-0.003136	-0.010849	-0.013333	-0.013440	0.381596	0.290851	0.344333	0.263607	0.195747	0.255733	0.131601	0.101520	0.268476	0.132008	0.348742	0.044116	0.069451	0.040012	0.058943	0.225430	0.149112	0.812857	0.845156	0.237520	1.000000	0.042663	0.053433	0.006529	0.008815	0.004158	0.002682	0.003736	0.200471	0.162028	0.112545	0.168249	0.099795	-0.044123	0.025836	0.245985	0.256055	0.248911	0.343829	-0.126084	-0.094560	0.057676	0.265784	0.139694	-0.131037	0.143604	0.164024	0.243916	-0.024729	0.812767
positive_rate	-0.031846	-0.022056	-0.022012	-0.027306	-0.012012	-0.012956	0.195474	0.273656	0.322341	0.241955	0.277142	0.351179	0.278298	0.047549	0.145015	0.084353	0.212793	0.024350	0.037480	0.028911	0.058813	0.051202	0.037691	0.044927	0.033105	0.053082	0.042663	1.000000	-0.058991	-0.024361	-0.023725	-0.020414	-0.023192	-0.026335	-0.010462	-0.007791	-0.004211	-0.025385	0.240022	-0.062133	-0.050031	0.173000	0.143001	0.121848	0.037632	-0.010264	-0.008149	0.050720	0.107091	0.075392	0.129802	0.036973	0.147607	0.188210	-0.004325	0.044093
tests_per_case	-0.016733	-0.019589	-0.019675	-0.018711	-0.020913	-0.021368	-0.042327	-0.044030	-0.051597	-0.049870	-0.038076	-0.049105	-0.003857	-0.010720	-0.021908	-0.012614	-0.022366	-0.004540	-0.004872	-0.004177	-0.005718	-0.006162	-0.000833	0.049600	0.022278	-0.000262	0.053433	-0.058991	1.000000	-0.007524	-0.007713	-0.007009	-0.007468	-0.008778	-0.009928	-0.010887	-0.007687	-0.012689	0.014732	-0.018997	0.036641	0.085796	0.070539	0.070695	0.092000	-0.045202	-0.053285	0.006502	0.024845	0.015216	0.006142	0.023809	0.064875	0.074257	0.004023	0.049402
total_vaccinations	0.712460	0.397744	0.401333	0.669213	0.409118	0.430561	0.102226	0.022416	0.027523	0.109466	0.027435	0.038331	-0.030006	0.061237	0.015185	0.055850	0.005429	0.000614	0.000057	0.021460	0.002126	0.078534	0.137186	0.023658	0.006281	0.082838	0.006529	-0.024361	-0.007524	1.000000	0.984913	0.959558	0.873713	0.964824	0.119421	0.123612	0.090652	0.085091	-0.075348	0.315723	-0.010179	-0.036691	-0.012138	-0.012318	-0.006516	-0.015322	-0.051589	-0.028209	-0.006913	-0.011725	-0.001298	-0.020740	-0.086622	-0.047325	-0.003114	0.023558
people_vaccinated	0.721331	0.406687	0.410950	0.682720	0.424122	0.446276	0.122091	0.029683	0.036373	0.133928	0.036775	0.051013	-0.029790	0.077725	0.022478	0.072310	0.010722	0.001050	0.000306	0.026770	0.003464	0.100568	0.168038	0.026456	0.008184	0.106041	0.008815	-0.023725	-0.007713	0.984913	1.000000	0.974682	0.856250	0.946347	0.129685	0.146595	0.100164	0.095252	-0.073444	0.292861	-0.010253	-0.035518	-0.008631	-0.008673	-0.004895	-0.015705	-0.054310	-0.029927	-0.003029	-0.012915	-0.002113	-0.021202	-0.086732	-0.046192	-0.002612	0.026353
people_fully_vaccinated	0.647483	0.342398	0.343239	0.612810	0.352113	0.371470	0.121083	0.026210	0.031766	0.125900	0.030197	0.042211	-0.026950	0.067141	0.017603	0.058997	0.006278	0.001984	0.001749	0.025660	0.002867	0.083422	0.162634	0.024571	0.003731	0.089119	0.004158	-0.020414	-0.007009	0.959558	0.974682	1.000000	0.808154	0.894264	0.140559	0.148035	0.130003	0.096718	-0.066482	0.248944	-0.009514	-0.031637	-0.007082	-0.007336	-0.001314	-0.015116	-0.048973	-0.025048	-0.000802	-0.011169	-0.004312	-0.017002	-0.077353	-0.040572	-0.002357	0.024481
new_vaccinations	0.692255	0.423192	0.425565	0.647635	0.443051	0.455294	0.090132	0.024383	0.029043	0.098081	0.031103	0.040850	-0.029028	0.066358	0.016815	0.061275	0.006866	-0.001056	-0.000885	0.023381	0.001525	0.077393	0.133376	0.016388	0.003077	0.082379	0.002682	-0.023192	-0.007468	0.873713	0.856250	0.808154	1.000000	0.898606	0.087841	0.093622	0.063411	0.072339	-0.075451	0.320024	-0.009953	-0.038275	-0.014370	-0.014398	-0.009842	-0.013650	-0.050285	-0.028380	-0.008651	-0.012563	0.001672	-0.021972	-0.087441	-0.049020	-0.002990	0.016287
new_vaccinations_smoothed	0.761850	0.456582	0.465270	0.712731	0.475503	0.499895	0.103926	0.027034	0.033740	0.111981	0.033353	0.046262	-0.031482	0.085930	0.021940	0.080168	0.009642	0.000735	-0.000365	0.031477	0.003501	0.092829	0.157880	0.020483	0.003613	0.099878	0.003736	-0.026335	-0.008778	0.964824	0.946347	0.894264	0.898606	1.000000	0.100218	0.106580	0.072626	0.085212	-0.078480	0.355228	-0.011229	-0.036711	-0.012020	-0.013082	-0.008709	-0.017673	-0.054846	-0.028315	-0.009451	-0.007207	-0.002070	-0.020629	-0.093004	-0.050424	-0.003787	0.020363
total_vaccinations_per_hundred	0.064043	0.026179	0.027150	0.055957	0.027266	0.029790	0.259621	0.128705	0.154717	0.172962	0.060029	0.081652	-0.022365	0.043712	0.087949	0.050661	0.075386	0.031182	0.052089	0.016201	0.018194	0.095845	0.117492	0.292694	0.169418	0.098991	0.200471	-0.010462	-0.009928	0.119421	0.129685	0.140559	0.087841	0.100218	1.000000	0.920406	0.895713	0.637910	-0.023546	-0.005572	0.035765	0.000798	0.031438	0.026587	0.073904	-0.053859	-0.083562	-0.009806	0.052964	0.009073	-0.063433	0.003132	0.039925	-0.005570	-0.012276	0.292585
people_vaccinated_per_hundred	0.072061	0.031040	0.032227	0.064971	0.033968	0.036938	0.270905	0.137584	0.163011	0.203572	0.074032	0.099024	-0.024410	0.055147	0.101489	0.065647	0.091120	0.033651	0.055773	0.020380	0.021654	0.103249	0.121656	0.224494	0.134741	0.106911	0.162028	-0.007791	-0.010887	0.123612	0.146595	0.148035	0.093622	0.106580	0.920406	1.000000	0.883910	0.637694	-0.016804	-0.006389	0.041421	0.001078	0.050346	0.045125	0.059672	-0.054998	-0.098857	-0.032715	0.069864	0.000928	-0.068011	0.011766	0.038354	-0.012543	-0.011118	0.224356
people_fully_vaccinated_per_hundred	0.046951	0.016871	0.017394	0.039945	0.017103	0.018876	0.205248	0.092042	0.112839	0.129116	0.042252	0.058145	-0.025124	0.029202	0.077630	0.031177	0.060146	0.031095	0.052405	0.011313	0.015675	0.047257	0.073759	0.169468	0.092311	0.050371	0.112545	-0.004211	-0.007687	0.090652	0.100164	0.130003	0.063411	0.072626	0.895713	0.883910	1.000000	0.511586	-0.022501	-0.005894	0.033394	-0.009741	0.029934	0.024746	0.037036	-0.038546	-0.073534	-0.029716	0.049227	0.000987	-0.051230	0.006811	0.032135	-0.015234	-0.008774	0.169373
new_vaccinations_smoothed_per_million	0.050862	0.019985	0.021369	0.042584	0.020999	0.023285	0.252964	0.144340	0.173611	0.167460	0.071417	0.095334	-0.055871	0.047276	0.078294	0.055944	0.075445	0.025843	0.043496	0.018172	0.016957	0.072714	0.094580	0.232605	0.140532	0.076593	0.168249	-0.025385	-0.012689	0.085091	0.095252	0.096718	0.072339	0.085212	0.637910	0.637694	0.511586	1.000000	-0.062090	-0.014736	0.084041	-0.070166	-0.008877	-0.012378	0.073063	-0.077464	-0.142423	-0.022857	0.027710	-0.034196	-0.084280	-0.004393	0.048746	-0.086491	-0.015533	0.232494
stringency_index	-0.145777	-0.161542	-0.161955	-0.162855	-0.168757	-0.172637	0.053885	0.065433	0.081502	0.072068	0.086211	0.115864	0.418285	0.072354	0.146991	0.088651	0.130899	0.028695	0.029328	0.026908	0.029986	0.097414	0.071742	0.087400	0.085473	0.105517	0.099795	0.240022	0.014732	-0.075348	-0.073444	-0.066482	-0.075451	-0.078480	-0.023546	-0.016804	-0.022501	-0.062090	1.000000	-0.196004	0.015782	0.292981	0.163459	0.141424	0.140551	-0.041664	0.159682	0.139259	0.127851	0.214056	0.138402	0.086831	0.330978	0.319636	0.025948	0.085257
population	0.604423	0.663643	0.666750	0.640210	0.680219	0.696445	-0.032970	-0.030167	-0.035172	-0.017455	-0.017140	-0.022001	-0.042620	0.008319	-0.027411	0.002755	-0.032721	-0.005558	-0.007745	0.002161	-0.007450	0.055545	0.051921	-0.044317	-0.034892	0.055763	-0.044123	-0.062133	-0.018997	0.315723	0.292861	0.248944	0.320024	0.355228	-0.005572	-0.006389	-0.005894	-0.014736	-0.196004	1.000000	-0.026475	-0.109728	-0.063724	-0.065860	-0.069954	-0.021502	-0.106085	-0.075385	-0.066850	-0.016019	0.032924	-0.061535	-0.235813	-0.146765	0.004704	-0.044641

Data Scientist Capstone¶

By Marwan Saeed Alsharabbi¶

COVID-19 Analysis ,visualization & Prediction¶

Definition

Project Overview¶

Select a real-world dataset¶

Data Sources:¶

License:¶

Authors:¶

Problem Statement¶

1- Created a Linear regression-Forecast model :¶

2- Create a model that can predict the risk of mortality for people over 65 years of age and over using KNN :¶

Metrics and Methodology¶

Linear regression-Forecast model¶

k-nearest neighbors(KNN) algorithm¶

Importing Libraries¶

Analysis

Data Exploration¶

In this link, every execution process pulls the new and updated data from the link¶

Step 2: Perform data preparation & Cleaning¶

Numerical Features¶

Categorical Features¶

Data Visualization

Data Visualization¶

Loading the cleaned Data and Exploring the histogram of the data looks like¶

It appears that each column contains values of a specific data type. You can view statistical information for numerical columns (mean, standard deviation, minimum/maximum values, and the number of non-empty values) using the .describe method.¶

Questions¶

Data Understanding¶

Question#1¶

How the many total population in each location by continents from our datase¶

Question#1¶

How the many total population in each location by continents from our datase¶

Question#2¶

The 10 top population total in each location by continents from our dataset¶

The 10 top population total in each location by continent 'Africa from our dataset¶

Create a data frame showing the total population of each continent¶

Question#3¶

Show countries in Asia,Europe and North America the total_cases and total_deaths,new_cases,total_tests, total_vaccinations by mean, and max¶

Question#4¶

Let's see the speed of transmission of the Corona virus between countries on the map .¶

Worldwide spread¶

We can see trend covid-19 moving to China -> Europe -> US¶

We can see trend covid-19 moving to China -> Europe -> US on map¶

Question#5¶

Let's see number of total_cases,total_deaths,total_deaths_per_million,test per confirmed(%) on map.¶

COVID-19 maps¶

Let's see number of confirmed cases on map.¶

Let's see number of deaths on map.¶

Let's see number of total deaths per million on map.¶

We can see that south,north America and europe has the most number of total deaths per million¶

Question#5¶

Top 15 countries for the total_cases,total_deaths,total_deaths_per_million,total_tests,people_fully_vaccinated and total_vaccinations on plot_hbar and Visulizing Treemaps¶

Top 15 countries¶

Visulizing Treemaps¶

Line Plot function¶

Question#6¶

How many the New Deaths Smoothed day by day in continents¶

Question#7¶

How many the new vaccinations smoothed day by day in continents¶

Question#8¶

How many the New Tests Smoothed day by day in continents¶

Question#8¶

How many the positive_rate day by day in continents¶

Test population coverage¶

Question#9¶

find some gdp_per_capita and new_cases clusters over countries¶

Question#10¶

find some new_deaths_smoothed_per_million, handwashing_facilities and extreme_poverty clusters over countries¶

Question#11¶

find some new_deaths_smoothed_per_million, aged_70_older and population_density clusters over countries¶

Question#12¶

find some new_deaths_smoothed_per_million, life_expectancy and hospital_beds_per_thousand clusters over countries¶

Stringency Index and death rate correlation¶

Modeling

Correlation Analysis¶

Linear Regression-Forecast

k-nearest neighbors(KNN) algorithm

I will create a model that can predict the risk for the Case Mortality Ratio of a Country utilizing its Life Expectancy, Percentage of Population over 65, and Percentage of diabetes_prevalence and cardiovasc_death_rate ? ¶

Correlation Analysis¶

We will be using the diabetes, cardiovascular health, percent of poplation above 70 and any other data we find to be the most useful to see if we can get better results with these features.¶